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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slug
    -0.07
    Experts
    -0.07
     Highway
    -0.07
    野
    -0.07
    Ted
    -0.06
    “When
    -0.06
    CAF
    -0.06
    CID
    -0.06
     CEO
    -0.06
    برد
    -0.06
    POSITIVE LOGITS
     esos
    0.07
    (trace
    0.07
     blaming
    0.07
    ."""
    0.07
     극
    0.06
     diğer
    0.06
     taşım
    0.06
    :NSLocalizedString
    0.06
    méně
    0.06
     Получ
    0.06
    Act Density 0.296%

    No Known Activations