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

    Neuronpedia

    INDEX
    Explanations

    surgeries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áhnout
    -0.07
    []"
    -0.06
    middlewares
    -0.06
    Cook
    -0.06
    _win
    -0.06
     glEnd
    -0.06
     Наг
    -0.06
     bulunmaktadır
    -0.06
     Mob
    -0.06
     broadcasts
    -0.06
    POSITIVE LOGITS
    .isArray
    0.06
    ppe
    0.06
    専
    0.06
    /exp
    0.06
     Sequence
    0.06
    碰
    0.06
    ينات
    0.06
    ρυ
    0.06
    (tableName
    0.06
    言
    0.06
    Act Density 0.013%

    No Known Activations