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

    Neuronpedia

    INDEX
    Explanations

    machine learning code and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ：
    0.45
    和
    0.43
     和
    0.42
    要知道
    0.42
    Rainbow
    0.41
    ကြီး
    0.40
     静
    0.40
    เน
    0.39
    Labs
    0.38
     ไม่มี
    0.38
    POSITIVE LOGITS
    ⱪ
    0.42
    lef
    0.41
    ческая
    0.41
    шив
    0.41
     shaded
    0.41
    kappa
    0.40
    bir
    0.40
     unsurprisingly
    0.40
    asının
    0.40
     específicamente
    0.39
    Act Density 0.001%

    No Known Activations