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

    Neuronpedia

    INDEX
    Explanations

    incel Community

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     G
    0.76
    ADP
    0.73
     ad
    0.71
    Adams
    0.71
    antro
    0.69
     Adams
    0.68
     ADP
    0.68
     Ad
    0.67
    Ad
    0.67
    ads
    0.66
    POSITIVE LOGITS
     মেন
    0.73
     noção
    0.71
    dana
    0.69
    idora
    0.69
    ె
    0.68
    शी
    0.66
    しの
    0.66
     Meier
    0.66
     मेंस
    0.66
    sb
    0.65
    Act Density 0.196%

    No Known Activations