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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CAP
    -0.07
    fork
    -0.07
    AccessException
    -0.06
     ça
    -0.06
    SAFE
    -0.06
    .allowed
    -0.06
    .GetById
    -0.06
     文章
    -0.06
    (.
    -0.06
    placements
    -0.06
    POSITIVE LOGITS
     Wich
    0.07
    'LBL
    0.07
    webpack
    0.07
     �
    0.07
     width
    0.06
    845
    0.06
    ।↵
    0.06
     barric
    0.06
     spirit
    0.06
    frican
    0.06
    Act Density 0.013%

    No Known Activations