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

    Neuronpedia

    INDEX
    Explanations

    specific nsfw or detailed subject matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fournis
    0.91
    Facilities
    0.88
     sociétés
    0.81
     patrons
    0.80
     cittadini
    0.79
     sociaux
    0.79
    Latitude
    0.79
    ర్చి
    0.78
    们
    0.78
    栉
    0.78
    POSITIVE LOGITS
    w
    0.81
    wirkungen
    0.73
    s
    0.73
     общий
    0.71
    ့
    0.70
    b
    0.70
    no
    0.69
     actúa
    0.68
    point
    0.68
    ري
    0.68
    Act Density 0.000%

    No Known Activations