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

    Neuronpedia

    INDEX
    Explanations

    exclamation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    סול
    -0.07
    nl
    -0.07
    建国
    -0.07
     Kısa
    -0.07
     paying
    -0.06
     recruiter
    -0.06
     deltaTime
    -0.06
     Açık
    -0.06
     Lam
    -0.06
    饹
    -0.06
    POSITIVE LOGITS
    إجراءات
    0.08
    .configuration
    0.07
    ❂
    0.07
    劣
    0.07
    外围
    0.07
     prow
    0.07
    роз
    0.07
    _iter
    0.07
    汉子
    0.07
    "](
    0.06
    Act Density 0.002%

    No Known Activations