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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dis
    -0.06
    currentUser
    -0.06
     readiness
    -0.06
     Elections
    -0.06
     záz
    -0.06
    _RUNTIME
    -0.06
    ApiClient
    -0.06
     Erdoğan
    -0.06
     commenter
    -0.06
     hayata
    -0.06
    POSITIVE LOGITS
    .record
    0.08
     Carl
    0.07
    erv
    0.06
    ‌ترین
    0.06
    ада
    0.06
    <Scalars
    0.06
    완료
    0.06
    seau
    0.06
    ламент
    0.06
    urs
    0.06
    Act Density 0.179%

    No Known Activations