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

    Neuronpedia

    INDEX
    Explanations

    rights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     labels
    -0.07
     saver
    -0.07
    cribed
    -0.07
    inar
    -0.06
    .Time
    -0.06
    technology
    -0.06
     ACCOUNT
    -0.06
    asured
    -0.06
    _interaction
    -0.06
     Loving
    -0.06
    POSITIVE LOGITS
     κι
    0.07
     เคร
    0.07
     refusing
    0.06
     khung
    0.06
     misdemeanor
    0.06
    osex
    0.06
    .BorderStyle
    0.06
    operative
    0.06
     편
    0.06
     TCHAR
    0.06
    Act Density 0.002%

    No Known Activations