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

    Neuronpedia

    INDEX
    Explanations

    bilateral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fo
    -0.07
    	ps
    -0.07
     Plains
    -0.07
    ังม
    -0.07
    groundColor
    -0.07
     mins
    -0.06
     worlds
    -0.06
     demande
    -0.06
     receptive
    -0.06
    CDF
    -0.06
    POSITIVE LOGITS
     bilateral
    0.09
     mutlaka
    0.07
     铁
    0.07
     informal
    0.07
    arParams
    0.06
     협
    0.06
     обрат
    0.06
     ↔
    0.06
     Invasion
    0.06
    νομα
    0.06
    Act Density 0.005%

    No Known Activations