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

    Neuronpedia

    INDEX
    Explanations

    define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kteří
    -0.07
     racially
    -0.07
    “If
    -0.07
    ´t
    -0.07
     těch
    -0.06
     banc
    -0.06
     Types
    -0.06
    .drawRect
    -0.06
    “How
    -0.06
    jaw
    -0.06
    POSITIVE LOGITS
     satisfaction
    0.07
     disruption
    0.07
     떨어
    0.07
     перет
    0.06
    -domain
    0.06
     departing
    0.06
     soutěže
    0.06
    extension
    0.06
     پیوند
    0.06
     العلم
    0.06
    Act Density 0.007%

    No Known Activations