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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     маг
    -0.07
    oğan
    -0.07
    ौन
    -0.06
     محصول
    -0.06
    $time
    -0.06
     přeb
    -0.06
    배송
    -0.06
     Iron
    -0.06
    .avi
    -0.06
     Tuesday
    -0.06
    POSITIVE LOGITS
     sense
    0.08
    atile
    0.07
    释
    0.07
    alore
    0.07
     accepting
    0.07
    bits
    0.07
     deserted
    0.06
    codes
    0.06
    ge
    0.06
    European
    0.06
    Act Density 0.047%

    No Known Activations