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

    Neuronpedia

    INDEX
    Explanations

    politician descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chanteuse
    -0.97
     désigne
    -0.85
    preneurship
    -0.84
     anarchist
    -0.81
    ardized
    -0.81
    āciju
    -0.80
    Condition
    -0.80
    lography
    -0.78
     Shareholders
    -0.78
    得意
    -0.77
    POSITIVE LOGITS
     inexperienced
    1.21
     proven
    1.12
     moderate
    1.08
     Harvard
    1.07
     outsider
    1.04
     experienced
    1.03
     techn
    0.93
    Proven
    0.93
    是一位
    0.91
     tested
    0.90
    Act Density 0.059%

    No Known Activations