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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trusted
    -0.07
    .money
    -0.07
    .categories
    -0.07
    .isSuccessful
    -0.06
    दम
    -0.06
     ITEM
    -0.06
    .ny
    -0.06
    单位
    -0.06
    -cancel
    -0.06
    .SwingConstants
    -0.06
    POSITIVE LOGITS
    **/↵
    0.07
    ुए
    0.06
     murder
    0.06
    Kay
    0.06
    xx
    0.06
    ************************************************************************
    0.06
    elog
    0.06
    >p
    0.06
                             ↵
    0.06
    جه
    0.06
    Act Density 0.000%

    No Known Activations