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

    Neuronpedia

    INDEX
    Explanations

    code configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .created
    -0.07
    urlpatterns
    -0.07
     Follow
    -0.07
    ETwitter
    -0.07
    _Offset
    -0.06
     จาก
    -0.06
     Evan
    -0.06
    ascript
    -0.06
    preced
    -0.06
     devast
    -0.06
    POSITIVE LOGITS
     redefine
    0.07
    िप
    0.06
     synthes
    0.06
    ו�
    0.06
    éro
    0.06
     hồng
    0.06
    شن
    0.06
     mañana
    0.06
    setProperty
    0.06
    익
    0.06
    Act Density 0.025%

    No Known Activations