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

    Neuronpedia

    INDEX
    Explanations

    Eq

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Table
    -0.07
    нести
    -0.07
     desi
    -0.06
     hygiene
    -0.06
    	cell
    -0.06
    |R
    -0.06
    LAST
    -0.06
     waste
    -0.06
     sclerosis
    -0.06
    207
    -0.06
    POSITIVE LOGITS
     南
    0.06
    .pag
    0.06
     Seam
    0.06
    ческой
    0.06
     itemId
    0.06
     léč
    0.06
     BindingFlags
    0.05
    inherits
    0.05
     nord
    0.05
    }/${
    0.05
    Act Density 0.004%

    No Known Activations