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

    Neuronpedia

    INDEX
    Explanations

    Property

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فکی
    -0.07
    Tam
    -0.06
    Fire
    -0.06
    .Excel
    -0.06
     především
    -0.06
    Difficulty
    -0.06
    Jet
    -0.06
     chicken
    -0.06
     бет
    -0.06
     genres
    -0.06
    POSITIVE LOGITS
    Pose
    0.08
     flushed
    0.07
    ervoir
    0.06
    цес
    0.06
    .getBy
    0.06
    >"
    0.06
    ुन
    0.06
    spo
    0.06
    indo
    0.06
    気が
    0.06
    Act Density 0.009%

    No Known Activations