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

    Neuronpedia

    INDEX
    Explanations

    code/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.60
    re
    0.56
     L
    0.54
    ar
    0.54
     I
    0.53
    ids
    0.52
    fe
    0.52
    år
    0.51
    hed
    0.50
    0
    0.50
    POSITIVE LOGITS
    !!”
    0.61
    ！”
    0.60
    !“
    0.58
    ᚑ
    0.56
    !!!"
    0.54
    ્સ
    0.52
    ,/*
    0.52
    ，”
    0.51
    ὦ
    0.51
    ”،
    0.50
    Act Density 0.000%

    No Known Activations