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

    Neuronpedia

    INDEX
    Explanations

    date and time strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पणे
    1.24
    is
    1.16
    נה
    1.10
    א
    1.09
    ur
    1.05
    el
    1.04
    ן
    1.04
    ं
    1.03
    en
    1.02
    ou
    1.01
    POSITIVE LOGITS
     кам
    0.99
    荿
    0.98
     RAID
    0.97
     AUTOM
    0.95
     боя
    0.95
    вые
    0.95
     redshift
    0.95
     лу
    0.92
     sábado
    0.92
     horas
    0.92
    Act Density 0.013%

    No Known Activations