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

    Neuronpedia

    INDEX
    Explanations

    how to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countDown
    0.48
    amerika
    0.40
     KMS
    0.40
    inando
    0.39
    ibl
    0.39
     pokaż
    0.39
    婁
    0.39
    ਖ਼
    0.39
    eiros
    0.38
    ]={"
    0.38
    POSITIVE LOGITS
     utilization
    0.62
    利用
    0.61
    活用
    0.57
     utilize
    0.56
    Utilization
    0.56
     Utilization
    0.53
     wykorzyst
    0.51
     utilizing
    0.49
     utilise
    0.48
     利用
    0.46
    Act Density 0.004%

    No Known Activations