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

    Neuronpedia

    INDEX
    Explanations

    [:

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shows
    -0.07
    IPP
    -0.07
     Warfare
    -0.07
     produces
    -0.06
     exhibition
    -0.06
     kaldı
    -0.06
    avigation
    -0.06
     climbs
    -0.06
     amatør
    -0.06
    shown
    -0.06
    POSITIVE LOGITS
     tod
    0.06
    libc
    0.06
     glGen
    0.06
    _GT
    0.06
     kaybet
    0.06
     وی
    0.06
     Beau
    0.06
    _quad
    0.06
    (dynamic
    0.06
    prepend
    0.06
    Act Density 0.001%

    No Known Activations