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

    Neuronpedia

    INDEX
    Explanations

    Political elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Balance
    -0.08
     Tas
    -0.07
     Apparently
    -0.07
    nictví
    -0.07
     Equivalent
    -0.07
    Indexes
    -0.07
    аря
    -0.07
    ує
    -0.07
    Apparently
    -0.07
    ette
    -0.07
    POSITIVE LOGITS
     schl
    0.06
     Eis
    0.06
    \:
    0.06
    \/\/
    0.05
    rych
    0.05
    νώ
    0.05
     lie
    0.05
     Aren
    0.05
     CIA
    0.05
    _include
    0.05
    Act Density 0.016%

    No Known Activations