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

    Neuronpedia

    INDEX
    Explanations

    government control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffe
    -0.07
     trhu
    -0.06
     Cindy
    -0.06
     GP
    -0.06
    Spoiler
    -0.06
     |=
    -0.06
    _eta
    -0.06
     Archie
    -0.06
    sqlite
    -0.06
    slash
    -0.06
    POSITIVE LOGITS
     organisations
    0.07
    vál
    0.06
    uji
    0.06
     ch
    0.06
    (__('
    0.06
    ebiliriz
    0.06
    lemetry
    0.06
    represent
    0.06
    	Method
    0.06
    、
    0.06
    Act Density 0.050%

    No Known Activations