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

    Neuronpedia

    INDEX
    Explanations

    CPU, vegetarian, Technical followed by connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒈
    0.41
     dolayı
    0.40
    ithecus
    0.40
    किसी
    0.39
     atof
    0.39
    欱
    0.39
    oarece
    0.38
    字符串
    0.37
    ColorBit
    0.37
    tbLabel
    0.37
    POSITIVE LOGITS
     versus
    0.80
     vs
    0.79
     maupun
    0.76
     Versus
    0.65
     Vs
    0.63
    -,
    0.59
    /
    0.57
     AND
    0.55
     lẫn
    0.54
    -
    0.54
    Act Density 0.209%

    No Known Activations