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

    Neuronpedia

    INDEX
    Explanations

    rendering pages (e.g., index, quiz)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     muitos
    0.63
     muchos
    0.61
    تی
    0.54
     filhos
    0.54
    तियाँ
    0.54
     yli
    0.52
    銚
    0.52
     escrit
    0.52
     cirugía
    0.52
    の写真
    0.52
    POSITIVE LOGITS
     a
    0.62
     cravings
    0.59
     T
    0.59
     instincts
    0.58
     W
    0.53
     to
    0.52
     contours
    0.52
     angles
    0.52
     beats
    0.52
     muscles
    0.51
    Act Density 0.001%

    No Known Activations