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

    Neuronpedia

    INDEX
    Explanations

    political ideologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spanking
    -0.08
     wlan
    -0.07
    ínu
    -0.07
     laughter
    -0.07
     Ashe
    -0.07
    [c
    -0.07
     getStatus
    -0.07
    	fwrite
    -0.07
    (gray
    -0.07
     unix
    -0.06
    POSITIVE LOGITS
    ализ
    0.06
    -demand
    0.06
    ismus
    0.05
    spect
    0.05
     Retro
    0.05
    aths
    0.05
     comme
    0.05
     Plans
    0.05
    озвращ
    0.05
    _DECLS
    0.05
    Act Density 0.025%

    No Known Activations