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

    Neuronpedia

    INDEX
    Explanations

    say trace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (New
    -0.08
    Blake
    -0.07
     Latinos
    -0.07
     merger
    -0.07
        ↵    ↵    ↵    ↵
    -0.07
     עסק
    -0.07
    🧚
    -0.07
     Barcode
    -0.07
     Laguna
    -0.07
     conte
    -0.07
    POSITIVE LOGITS
    raft
    0.07
    URL
    0.07
     slippery
    0.07
    pon
    0.07
     ile
    0.07
    _GLOBAL
    0.07
    .getP
    0.07
    _of
    0.06
    оя
    0.06
     fro
    0.06
    Act Density 0.003%

    No Known Activations