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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.63
     ++)
    -0.62
    DebuggerNonUser
    -0.61
    DeleteBehavior
    -0.60
    المشاركات
    -0.60
     Catawiki
    -0.60
    Externé
    -0.56
     newBuilder
    -0.54
    lichung
    -0.53
     ModelExpression
    -0.51
    POSITIVE LOGITS
     cherchés
    0.47
     coal
    0.46
    pergillus
    0.45
    athyroid
    0.44
    TextSpan
    0.43
     guld
    0.43
     cadeiras
    0.43
    Gön
    0.43
     desaf
    0.42
    DateUtils
    0.42
    Act Density 0.001%

    No Known Activations