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

    Neuronpedia

    INDEX
    Explanations

    writing erotica

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.04
    0.93
     pensar
    0.82
    TZ
    0.82
    1
    0.74
     europeo
    0.73
     hitters
    0.73
     sorta
    0.73
     sabato
    0.73
    C
    0.73
    POSITIVE LOGITS
    ্ত্র
    0.91
    <unused2064>
    0.88
    <unused217>
    0.86
    <unused294>
    0.83
    <unused426>
    0.83
    <unused301>
    0.81
    <unused2002>
    0.81
     Scholarships
    0.81
    ೨
    0.81
    <unused588>
    0.80
    Act Density 0.756%

    No Known Activations