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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Format
    -0.06
    apphire
    -0.06
     EOF
    -0.06
     seed
    -0.06
     nurses
    -0.06
    _SID
    -0.06
    Clock
    -0.06
     fuss
    -0.06
    nullable
    -0.06
    istration
    -0.06
    POSITIVE LOGITS
    __':
↵
    0.06
    ництва
    0.06
     puan
    0.06
     aş
    0.06
    Gb
    0.06
    ban
    0.06
    ­n
    0.06
    /script
    0.06
    ///↵↵
    0.06
     (%)
    0.06
    Act Density 0.037%

    No Known Activations