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

    Neuronpedia

    INDEX
    Explanations

    explanation of a pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    耒
    0.43
    uzzi
    0.40
    каз
    0.39
     topping
    0.39
    あの
    0.39
    tuvo
    0.39
    깍
    0.38
     あの
    0.38
     quant
    0.38
     agar
    0.38
    POSITIVE LOGITS
     visible
    0.47
     presumably
    0.46
     बाकी
    0.46
    presumably
    0.43
     njima
    0.41
     drugih
    0.41
     sister
    0.40
     primeiros
    0.40
    Their
    0.39
     público
    0.38
    Act Density 0.003%

    No Known Activations