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

    Neuronpedia

    INDEX
    Explanations

    definition of a term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نے
    0.82
    房间
    0.81
    >`;
    0.81
    ()`
    0.78
    Doctors
    0.78
    ب
    0.74
    Email
    0.73
     とする
    0.72
    将
    0.71
    Θ
    0.71
    POSITIVE LOGITS
     aggregation
    0.83
     aggregated
    0.80
     aggregator
    0.77
     nonnegative
    0.75
     barcodes
    0.75
     automation
    0.75
     outputs
    0.74
     INTE
    0.73
     Austro
    0.73
     individuality
    0.72
    Act Density 0.001%

    No Known Activations