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

    Neuronpedia

    INDEX
    Explanations

    named after saints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weil
    -0.07
    retch
    -0.07
    ेवल
    -0.07
     So
    -0.07
    (sn
    -0.06
    said
    -0.06
    entifier
    -0.06
    ism
    -0.06
    _refptr
    -0.06
    ombres
    -0.06
    POSITIVE LOGITS
    dol
    0.07
     rethink
    0.07
    DG
    0.06
    .Db
    0.06
     Gutenberg
    0.06
     Newton
    0.06
    alus
    0.06
    alternate
    0.06
     DG
    0.06
     aden
    0.06
    Act Density 0.028%

    No Known Activations