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

    Neuronpedia

    INDEX
    Explanations

    electricity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UMAN
    -0.08
    SEN
    -0.07
    Span
    -0.07
    Mean
    -0.07
    Rose
    -0.07
     Jews
    -0.07
    uman
    -0.07
     Brendan
    -0.07
    al
    -0.07
    Tan
    -0.06
    POSITIVE LOGITS
     electricity
    0.11
     Electricity
    0.10
     четвер
    0.07
    .DotNetBar
    0.07
     şüph
    0.07
     nút
    0.07
     желез
    0.07
    !!}</
    0.07
     stones
    0.06
     principio
    0.06
    Act Density 0.003%

    No Known Activations