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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warranted
    -0.08
    .CreateDirectory
    -0.07
     Dong
    -0.07
     memory
    -0.07
    _LOW
    -0.07
    World
    -0.06
     보내
    -0.06
     Entertainment
    -0.06
     있어
    -0.06
     Lighting
    -0.06
    POSITIVE LOGITS
    країн
    0.06
    켓
    0.06
    शन
    0.06
     Mickey
    0.06
     řid
    0.06
    ęp
    0.06
    asionally
    0.06
     сент
    0.06
    IsEmpty
    0.06
    تور
    0.06
    Act Density 0.041%

    No Known Activations