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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kok
    -0.07
    Mountain
    -0.07
    роничес
    -0.07
     worsh
    -0.07
    Lista
    -0.07
    Bound
    -0.07
    Colorado
    -0.06
    /player
    -0.06
     내려
    -0.06
     HV
    -0.06
    POSITIVE LOGITS
     using
    0.08
     Kim
    0.07
    ([]
    0.06
     đang
    0.06
    lbrakk
    0.06
     Specifications
    0.06
    .Serialization
    0.06
    akit
    0.06
    칭
    0.06
    []=$
    0.06
    Act Density 0.019%

    No Known Activations