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

    Neuronpedia

    INDEX
    Explanations

    electrical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    포
    -0.08
    GetProperty
    -0.07
     Icelandic
    -0.07
     owning
    -0.07
    جائزة
    -0.07
    Scalars
    -0.07
     Named
    -0.07
     evaluation
    -0.07
     chase
    -0.06
    נל
    -0.06
    POSITIVE LOGITS
    .amazon
    0.07
    	inter
    0.07
    requent
    0.07
    -react
    0.07
     Washing
    0.07
    unistd
    0.06
    coords
    0.06
    (dim
    0.06
     שונות
    0.06
    eway
    0.06
    Act Density 0.044%

    No Known Activations