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

    Neuronpedia

    INDEX
    Explanations

    numbers and arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alternativ
    0.68
     OECD
    0.67
     USC
    0.66
     peduncul
    0.66
     TIT
    0.66
     corr
    0.65
     FURTHER
    0.65
     Eds
    0.65
     fiets
    0.64
     Пен
    0.64
    POSITIVE LOGITS
    所の
    0.78
    的不
    0.71
    yer
    0.69
    ерез
    0.69
    等を
    0.67
    ClInclude
    0.66
    等
    0.66
     clamped
    0.66
    克的
    0.66
    打破
    0.66
    Act Density 0.070%

    No Known Activations