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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sax
    0.40
    భ్య
    0.40
    DIY
    0.39
    Ｑ
    0.39
    XC
    0.39
     CXCR
    0.38
     XLR
    0.38
     මත
    0.38
     юм
    0.38
     Produ
    0.38
    POSITIVE LOGITS
    dec
    0.53
    ce
    0.52
    ed
    0.46
    ffe
    0.46
    af
    0.45
    fa
    0.45
    ffa
    0.44
    ff
    0.43
    ca
    0.43
    bee
    0.43
    Act Density 0.009%

    No Known Activations