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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GRAM
    -0.07
     rostlin
    -0.07
     міської
    -0.07
    -three
    -0.07
    /button
    -0.06
    (gp
    -0.06
    reserved
    -0.06
     сохран
    -0.06
    enser
    -0.06
    .integer
    -0.06
    POSITIVE LOGITS
     полез
    0.07
     효
    0.07
     liked
    0.06
    利
    0.06
     plug
    0.06
    Compose
    0.06
     phương
    0.06
    asını
    0.06
     likes
    0.06
    Someone
    0.06
    Act Density 0.007%

    No Known Activations