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

    Neuronpedia

    INDEX
    Explanations

    serializer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vulgar
    -0.07
     domicile
    -0.06
     zwe
    -0.06
    .getFont
    -0.06
     جغراف
    -0.06
     Ä
    -0.06
    .getFile
    -0.06
     versatility
    -0.06
    kaz
    -0.06
    _prog
    -0.06
    POSITIVE LOGITS
    istrov
    0.07
    omidou
    0.07
     Dod
    0.06
    poses
    0.06
    342
    0.06
     taken
    0.06
     cooperating
    0.06
     inconsistency
    0.06
    един
    0.06
     synthesis
    0.06
    Act Density 0.008%

    No Known Activations