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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zen
    -0.07
    curity
    -0.07
     Resets
    -0.06
     iVar
    -0.06
     queryParams
    -0.06
    eczy
    -0.06
     można
    -0.06
     ascii
    -0.06
    Pressed
    -0.06
    /*@
    -0.06
    POSITIVE LOGITS
     متخصص
    0.07
    ל
    0.07
     Superintendent
    0.07
    <Vertex
    0.07
     permit
    0.06
     Dew
    0.06
     delivers
    0.06
     питания
    0.06
    (Query
    0.06
     fr
    0.06
    Act Density 0.003%

    No Known Activations