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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     руки
    -0.07
     rapor
    -0.07
    swick
    -0.06
    .Matchers
    -0.06
     dispensaries
    -0.06
    dess
    -0.06
     shoulders
    -0.06
    ара
    -0.06
    ibi
    -0.06
     Herb
    -0.06
    POSITIVE LOGITS
     directory
    0.07
     toxicity
    0.07
     PX
    0.06
     locom
    0.06
     pantalla
    0.06
    	setState
    0.06
    .TR
    0.06
     Matlab
    0.06
     assigning
    0.06
    .wallet
    0.06
    Act Density 0.024%

    No Known Activations