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

    Neuronpedia

    INDEX
    Explanations

    option letters 'c' and 'C'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     C
    0.43
     B
    0.41
    सीबी
    0.40
    adne
    0.40
     SBA
    0.38
     কুল
    0.37
     conc
    0.36
     ಸ
    0.36
     undert
    0.35
     フレ
    0.35
    POSITIVE LOGITS
    zd
    0.47
    SD
    0.38
    考える
    0.38
    Third
    0.37
    ZD
    0.37
     zd
    0.37
    يمق
    0.37
    زل
    0.36
    壢
    0.36
    embre
    0.34
    Act Density 0.016%

    No Known Activations