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

    Neuronpedia

    INDEX
    Explanations

    technical code and web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁈
    0.72
    昕
    0.72
    قتها
    0.70
     Dep
    0.69
    ANTH
    0.67
     bırak
    0.67
     کو
    0.66
     plent
    0.65
    anting
    0.65
     Freitas
    0.65
    POSITIVE LOGITS
    WD
    0.78
     Nal
    0.75
     GW
    0.71
     कारखाना
    0.68
    wd
    0.67
     recomm
    0.66
     Deepak
    0.66
    baikan
    0.65
     municipal
    0.65
     carpet
    0.64
    Act Density 0.001%

    No Known Activations