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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consultant
    -0.06
     dissertation
    -0.06
    _preference
    -0.06
    .svg
    -0.06
     Hut
    -0.06
    cid
    -0.06
    <D
    -0.06
    atore
    -0.06
    {}\
    -0.06
     Constraints
    -0.06
    POSITIVE LOGITS
    vou
    0.07
    kou
    0.07
    Та
    0.07
    amız
    0.07
     use
    0.06
    fastcall
    0.06
    usable
    0.06
    çı
    0.06
    __()↵
    0.06
    ไ
    0.06
    Act Density 0.009%

    No Known Activations