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

    Neuronpedia

    INDEX
    Explanations

    cute people descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أش
    0.54
    đer
    0.48
     אות
    0.48
     أول
    0.47
     apel
    0.47
     था
    0.46
    aop
    0.45
     hudson
    0.45
    …?
    0.45
    ština
    0.44
    POSITIVE LOGITS
    на
    0.53
    ба
    0.52
     sostegno
    0.51
    ισμού
    0.50
    いない
    0.48
    や
    0.48
    налу
    0.47
    yphenyl
    0.47
    Acetyl
    0.47
     necessario
    0.46
    Act Density 0.001%

    No Known Activations