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

    Neuronpedia

    INDEX
    Explanations

    Scientific references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    da
    -0.07
    =%.
    -0.07
    (BigDecimal
    -0.07
    ags
    -0.07
     Exodus
    -0.07
    esin
    -0.06
    .param
    -0.06
    万
    -0.06
    san
    -0.06
    -
↵
    -0.06
    POSITIVE LOGITS
     Casey
    0.07
     clearer
    0.06
     Sexe
    0.06
     모르
    0.06
    移動
    0.06
     CLR
    0.06
    ॉड
    0.06
    _COLORS
    0.06
     döneminde
    0.06
    허
    0.06
    Act Density 0.006%

    No Known Activations