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

    Neuronpedia

    INDEX
    Explanations

    configuration and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    थिक
    0.52
     contraceptives
    0.51
    itation
    0.50
    abby
    0.47
     वस्तू
    0.47
    artista
    0.46
    ocysts
    0.46
    kys
    0.46
    ल्स
    0.46
    ienda
    0.46
    POSITIVE LOGITS
     RAT
    0.44
     taz
    0.44
     खुलासा
    0.40
     Subsequent
    0.40
     SH
    0.40
    の中から
    0.40
     pow
    0.39
     kao
    0.39
     Chromat
    0.39
     tt
    0.38
    Act Density 0.000%

    No Known Activations