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

    Neuronpedia

    INDEX
    Explanations

    Sometimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    All
    -0.07
     all
    -0.07
    769
    -0.07
    (all
    -0.07
     привести
    -0.07
    Deal
    -0.07
     вероят
    -0.06
    Buy
    -0.06
    q
    -0.06
     ناحیه
    -0.06
    POSITIVE LOGITS
     sometimes
    0.17
    sometimes
    0.14
     Sometimes
    0.14
    Sometimes
    0.12
    ometimes
    0.10
     occasionally
    0.10
     sometime
    0.09
     někdy
    0.08
    isu
    0.08
    asionally
    0.08
    Act Density 0.011%

    No Known Activations