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

    Neuronpedia

    INDEX
    Explanations

    phrases with common question words and associated words like "then" and "or," often in sentences indicating a user looking for help

    oai_token-act-pair · gemini-2.0-flash

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.83
     resourceCulture
    -0.73
     photolibrary
    -0.70
    ReusableCell
    -0.65
    NamedQuery
    -0.65
    elemField
    -0.63
    prefixer
    -0.63
     myſelf
    -0.62
     withal
    -0.62
     ArrayAdapter
    -0.61
    POSITIVE LOGITS
    chaun
    0.44
    !
    0.43
    ?
    0.43
     tématu
    0.42
    argout
    0.42
    مصادر
    0.42
     !
    0.41
    ριθ
    0.41
    ,
    0.40
    res
    0.40
    Act Density 0.830%

    No Known Activations