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

    Neuronpedia

    INDEX
    Explanations

    detecting code errors or crashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bonded
    0.36
     disfruta
    0.36
     свое
    0.35
     만큼
    0.34
    夠
    0.34
     bead
    0.33
    គួរ
    0.33
    賊
    0.33
     softwood
    0.32
     probiotic
    0.32
    POSITIVE LOGITS
     errors
    0.89
    错误
    0.86
    エラー
    0.83
    报错
    0.82
     오류
    0.82
     error
    0.79
     Errors
    0.77
     erros
    0.75
    Errors
    0.73
    Error
    0.72
    Act Density 0.415%

    No Known Activations