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

    Neuronpedia

    INDEX
    Explanations

    ratios and proportions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _upgrade
    -0.08
     ọrụ
    -0.08
    остоя
    -0.08
    DEC
    -0.08
    Upgrade
    -0.08
     upgrade
    -0.07
    pụ
    -0.07
     Anspruch
    -0.07
    녕하세요
    -0.07
    _BAD
    -0.07
    POSITIVE LOGITS
     normalized
    0.10
     normalization
    0.09
     relativo
    0.09
    normalized
    0.09
     relativa
    0.08
     calibrated
    0.08
     ratios
    0.08
     Compar
    0.08
     comparable
    0.08
     Nome
    0.08
    Act Density 0.025%

    No Known Activations