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

    Neuronpedia

    INDEX
    Explanations

    tag archives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rays
    -0.07
     Finch
    -0.06
     lux
    -0.06
    osis
    -0.06
    stood
    -0.06
    dete
    -0.06
    کس
    -0.06
    _two
    -0.06
    λογ
    -0.06
     insults
    -0.06
    POSITIVE LOGITS
     mildly
    0.06
    .Net
    0.06
    ована
    0.06
     مي
    0.06
     tlak
    0.06
     pledged
    0.06
    (case
    0.06
     acknowled
    0.06
    าภ
    0.06
    عات
    0.06
    Act Density 0.005%

    No Known Activations