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

    Neuronpedia

    INDEX
    Explanations

    occurrences related to context switches or transitions in data or systems

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

    that express uncertainty or possibility

    np_acts-logits-general · gemini-2.0-flash

    whether or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poichè
    -0.62
     feroit
    -0.59
    utilisons
    -0.58
     étoit
    -0.56
     auroit
    -0.56
     nearby
    -0.56
     endast
    -0.55
    Bronnen
    -0.54
     هنگام
    -0.53
     الرياضيه
    -0.52
    POSITIVE LOGITS
     really
    0.93
     basically
    0.85
     uh
    0.84
     actually
    0.83
     sort
    0.83
     stuff
    0.83
     kind
    0.82
     [
    0.80
     somebody
    0.79
     veldig
    0.76
    Act Density 0.499%

    No Known Activations