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

    Neuronpedia

    INDEX
    Explanations

    oss and mss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mora
    -0.79
    ENEZ
    -0.76
    dee
    -0.76
    ása
    -0.75
    🗃
    -0.74
    aria
    -0.73
     наступа
    -0.72
     зер
    -0.72
    все
    -0.71
     Edel
    -0.71
    POSITIVE LOGITS
    малар
    0.82
     mantiene
    0.78
    Oss
    0.73
    GV
    0.71
     MSS
    0.71
    SB
    0.70
     OSS
    0.70
     위한
    0.70
    athe
    0.69
    LError
    0.69
    Act Density 0.027%

    No Known Activations