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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     queda
    -0.08
     편
    -0.07
    Insets
    -0.07
     surrounds
    -0.07
     intestinal
    -0.07
     acepta
    -0.07
    mary
    -0.07
    yon
    -0.07
    agar
    -0.07
     pull
    -0.07
    POSITIVE LOGITS
     تعداد
    0.12
     সংখ্যা
    0.10
     количество
    0.10
     Anzahl
    0.10
     হিস
    0.10
    Количество
    0.10
     რაოდენ
    0.09
     количества
    0.09
     কত
    0.09
     कित
    0.09
    Act Density 0.079%

    No Known Activations