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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Degrees
    -0.07
    .samples
    -0.06
    unidad
    -0.06
    cılar
    -0.06
    039
    -0.06
    	cli
    -0.06
     enthusiastically
    -0.06
    안
    -0.06
    $db
    -0.06
    orce
    -0.06
    POSITIVE LOGITS
     ง
    0.07
    okia
    0.07
    _transition
    0.06
    -results
    0.06
     demographic
    0.06
    groundColor
    0.06
     bracket
    0.06
     تصویر
    0.06
    (det
    0.06
    (trace
    0.06
    Act Density 0.026%

    No Known Activations