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

    Neuronpedia

    INDEX
    Explanations

    list items and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nurseries
    0.50
     R
    0.49
     OF
    0.48
     OTP
    0.48
    0.47
    ので
    0.47
     Organic
    0.46
     О
    0.46
     spaces
    0.45
     line
    0.45
    POSITIVE LOGITS
    Einstein
    0.47
    大脑
    0.44
    Evaluating
    0.44
    Loading
    0.44
    ิค
    0.44
    Wedding
    0.42
    =:
    0.42
    عدة
    0.42
    də
    0.41
    Clothing
    0.41
    Act Density 0.000%

    No Known Activations