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

    Neuronpedia

    INDEX
    Explanations

    template placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    1.47
    [
    1.44
     [
    1.37
     hydrochloride
    1.29
    [{
    1.29
     ample
    1.16
     irrit
    1.14
     asympt
    1.12
     ist
    1.12
    [^
    1.12
    POSITIVE LOGITS
    ⿷
    1.74
    Архівовано
    1.49
    crayon
    1.48
    duplicate
    1.38
    Sexual
    1.37
    +]
    1.37
    ?]
    1.35
    Então
    1.33
    tpVar
    1.32
    ১
    1.30
    Act Density 0.131%

    No Known Activations