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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tud
    -0.07
    ock
    -0.07
    받
    -0.06
    zes
    -0.06
    undos
    -0.06
     Bair
    -0.06
    Wat
    -0.06
    .enemy
    -0.06
    gere
    -0.06
    ‌ی
    -0.06
    POSITIVE LOGITS
    <H
    0.06
     Captain
    0.06
    .",↵
    0.06
    .';↵
    0.06
     emotionally
    0.06
     '#
    0.06
     '=',
    0.06
     requisite
    0.06
    Captain
    0.06
     "]");↵
    0.06
    Act Density 0.002%

    No Known Activations