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

    Neuronpedia

    INDEX
    Explanations

    activities and states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     બીજા
    0.83
     लगे
    0.78
     svého
    0.77
    地の
    0.76
     svých
    0.76
     excelentes
    0.75
     inches
    0.74
     দর্শকের
    0.74
    以外の
    0.73
     interesantes
    0.72
    POSITIVE LOGITS
     Dz
    0.66
    페이스
    0.60
    ವೆ
    0.60
    ֖
    0.59
    bcrypt
    0.58
    ֔
    0.58
    ག
    0.58
    ृती
    0.58
    bigcap
    0.57
    ದೆ
    0.57
    Act Density 0.441%

    No Known Activations