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

    Neuronpedia

    INDEX
    Explanations

    Surgery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geometry
    -0.07
    import
    -0.07
     ffm
    -0.06
    čník
    -0.06
    杀
    -0.06
    ibrated
    -0.06
     awful
    -0.06
     Symbol
    -0.06
    gado
    -0.06
     zákon
    -0.06
    POSITIVE LOGITS
    IRTUAL
    0.07
    <Node
    0.07
    0.07
     remarked
    0.07
    ,''
    0.06
    abler
    0.06
    .KeyChar
    0.06
     Ihnen
    0.06
     nuestras
    0.06
     kanal
    0.06
    Act Density 0.036%

    No Known Activations