Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate exceptions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "unless" or a condition

    np_acts-logits-general · gemini-2.0-flash

    unless and explicit conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.70
    tagHelperRunner
    -0.64
    Anywhere
    -0.63
    anywhere
    -0.63
    Geplaatst
    -0.63
    hasMoreElements
    -0.61
     Anywhere
    -0.61
     hés
    -0.60
    abestanden
    -0.60
     estimés
    -0.60
    POSITIVE LOGITS
     explicitly
    1.18
     expressly
    1.14
     specifically
    1.14
     absolutely
    0.95
    rungsseite
    0.94
    specifically
    0.92
    absolutely
    0.87
     específicamente
    0.86
     otherwise
    0.86
     actively
    0.86
    Act Density 0.448%

    No Known Activations