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

    Neuronpedia

    INDEX
    Explanations

    case sensitivity discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ud
    0.58
    CA
    0.49
    gg
    0.45
    plotlib
    0.44
     using
    0.43
    using
    0.43
     Using
    0.43
    """
    0.43
    https
    0.43
     utilizzare
    0.42
    POSITIVE LOGITS
    谟
    0.55
    冠军
    0.49
    啬
    0.48
     dacă
    0.48
     shifter
    0.47
     complexion
    0.46
    infodisc
    0.46
     както
    0.46
    𒅴
    0.44
    onitrile
    0.43
    Act Density 0.002%

    No Known Activations