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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guitar
    -0.07
    ecture
    -0.07
     Flight
    -0.07
    _release
    -0.07
    _X
    -0.07
    .upper
    -0.06
     breadth
    -0.06
    但
    -0.06
     Tonight
    -0.06
    었
    -0.06
    POSITIVE LOGITS
     DEVICE
    0.07
    湲
    0.06
    ;element
    0.06
     Bild
    0.06
    genden
    0.06
    ?,?,?,?,
    0.06
    ="<?=
    0.06
    LocalizedString
    0.06
     bidding
    0.06
    bild
    0.06
    Act Density 0.003%

    No Known Activations