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

    Neuronpedia

    INDEX
    Explanations

    Asking for help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ras
    -0.08
    люд
    -0.07
     ludicrous
    -0.07
     soak
    -0.07
     Temple
    -0.07
     Yup
    -0.06
    (IL
    -0.06
    ecret
    -0.06
    ak
    -0.06
     D
    -0.06
    POSITIVE LOGITS
     sene
    0.06
    WithType
    0.06
    _study
    0.06
     bildir
    0.06
    _adjust
    0.06
     Marx
    0.06
    标
    0.06
     succession
    0.06
    .figure
    0.06
    WithError
    0.06
    Act Density 0.052%

    No Known Activations