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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fh
    -0.06
     کتاب
    -0.06
    死
    -0.06
    _users
    -0.06
    :r
    -0.06
    Postal
    -0.06
    έ
    -0.06
     ادبی
    -0.06
     childish
    -0.06
    remember
    -0.06
    POSITIVE LOGITS
    woke
    0.07
    werk
    0.06
    umped
    0.06
    -setup
    0.06
    abeled
    0.06
     souha
    0.06
    аж
    0.06
    对方
    0.06
     Hanging
    0.06
    .Horizontal
    0.06
    Act Density 0.090%

    No Known Activations