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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical symbols related to equations and constraints

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

    Numbers followed by currency symbols or periods

    np_acts-logits-general · gemini-2.0-flash

    mathematical punctuation and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.65
     Infórmanos
    -0.63
     Normdatei
    -0.59
    GEBURTSDATUM
    -0.59
    ftagPool
    -0.54
    YourGuide
    -0.53
    URLException
    -0.52
    ContentAsync
    -0.51
     Geiſt
    -0.50
    autaire
    -0.50
    POSITIVE LOGITS
    pushFollow
    0.37
     Lambert
    0.36
    bedingt
    0.36
    ("")]
    0.35
    NewUser
    0.35
    clue
    0.35
     Russel
    0.34
    ´
    0.34
    LOSS
    0.33
    大
    0.33
    Act Density 0.817%

    No Known Activations