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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Safe
    -0.07
    박
    -0.07
    _Type
    -0.07
     İç
    -0.07
    <Guid
    -0.06
    \Security
    -0.06
    natural
    -0.06
     abduction
    -0.06
    真爱
    -0.06
     Michele
    -0.06
    POSITIVE LOGITS
    湝
    0.07
    嵲
    0.07
    ":{"
    0.07
    涯
    0.07
    فيل
    0.07
     opponents
    0.07
    ╯
    0.06
    峛
    0.06
    силь
    0.06
    (worker
    0.06
    Act Density 0.002%

    No Known Activations