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

    Neuronpedia

    INDEX
    Explanations

    output and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     turismo
    0.43
    egg
    0.42
     छेद
    0.42
     வயி
    0.41
    फोर
    0.40
    権利
    0.40
    ᵒ
    0.40
     peanut
    0.39
    ້ມ
    0.39
    getBalance
    0.39
    POSITIVE LOGITS
     error
    0.69
     output
    0.68
     errors
    0.66
    Output
    0.65
     Output
    0.64
     Error
    0.62
    error
    0.61
    Error
    0.60
    output
    0.59
    エラー
    0.52
    Act Density 0.001%

    No Known Activations