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

    Neuronpedia

    INDEX
    Explanations

    code comments and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Both
    0.42
    ----------------
    0.42
     கீ
    0.39
    avacan
    0.39
     கரைச
    0.39
     To
    0.39
    SCRIPT
    0.38
    行く
    0.38
     STUDIO
    0.38
     PROCUREMENT
    0.38
    POSITIVE LOGITS
    这是
    0.43
    +',
    0.39
     a
    0.38
    Iv
    0.37
     biologists
    0.37
    một
    0.37
     einer
    0.36
    cds
    0.36
    இது
    0.36
     arisen
    0.36
    Act Density 0.001%

    No Known Activations