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

    Neuronpedia

    INDEX
    Explanations

    Greater than or equal to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planer
    -0.09
    dx
    -0.08
    Plat
    -0.07
    Pete
    -0.07
     dx
    -0.07
     scal
    -0.07
    628
    -0.07
    plat
    -0.07
     considerate
    -0.07
     perspective
    -0.07
    POSITIVE LOGITS
     प्रतिशत
    0.12
     ശതമ
    0.12
     শতাংশ
    0.12
    百分
    0.12
    _percentage
    0.11
    Percentage
    0.11
     Quality
    0.11
     Percentage
    0.11
     ટકા
    0.11
     Reliability
    0.11
    Act Density 0.037%

    No Known Activations