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

    Neuronpedia

    INDEX
    Explanations

    .js files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ktoré
    1.01
    मस्कार
    0.95
    ческие
    0.95
     homotopic
    0.93
     специальные
    0.93
     дочь
    0.92
     resor
    0.91
    тивные
    0.89
    ские
    0.89
    ческих
    0.88
    POSITIVE LOGITS
    Min
    0.72
    TBL
    0.72
     be
    0.71
    WARE
    0.70
    TRA
    0.69
    1
    0.68
    2
    0.68
    row
    0.67
    onna
    0.67
    tweet
    0.66
    Act Density 0.000%

    No Known Activations