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

    Neuronpedia

    INDEX
    Explanations

    sort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Closure
    -0.07
    .Rect
    -0.07
    ロ
    -0.06
     tener
    -0.06
     contractual
    -0.06
    _CYCLE
    -0.06
     Pil
    -0.06
     cherish
    -0.06
     segmentation
    -0.06
     zł
    -0.06
    POSITIVE LOGITS
    cente
    0.08
    leyici
    0.07
     اجتماعی
    0.07
    ORM
    0.07
    _students
    0.07
    second
    0.06
     σει
    0.06
     PIE
    0.06
    ulating
    0.06
    饰
    0.06
    Act Density 0.011%

    No Known Activations