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

    Neuronpedia

    INDEX
    Explanations

    error codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     always
    -0.87
     vescovo
    -0.86
    ᐈ
    -0.83
     of
    -0.82
     years
    -0.81
     still
    -0.79
     did
    -0.78
    atsby
    -0.78
     year
    -0.77
     doubt
    -0.77
    POSITIVE LOGITS
     code
    1.27
     codes
    1.25
    ErrorCode
    1.16
     códigos
    1.14
     errorCode
    1.10
     코드
    1.08
     kär
    1.05
     Code
    1.05
     Codes
    1.05
    codes
    0.99
    Act Density 0.033%

    No Known Activations