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

    Neuronpedia

    INDEX
    Explanations

    proportions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    覆盖
    -0.09
    合
    -0.08
     meld
    -0.08
    합
    -0.07
     finalize
    -0.07
     reversed
    -0.07
     mété
    -0.07
    -0.07
     могу
    -0.07
    _PID
    -0.07
    POSITIVE LOGITS
     proporcional
    0.16
     proportion
    0.16
     proportional
    0.14
     proportions
    0.13
     increases
    0.11
     ratios
    0.11
     equally
    0.11
     parehong
    0.11
     увелич
    0.11
     оба
    0.11
    Act Density 0.034%
    No Known Activations