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

    Neuronpedia

    INDEX
    Explanations

    tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parsers
    -0.07
     uh
    -0.06
    кта
    -0.06
     Wants
    -0.06
     Although
    -0.06
    “How
    -0.06
    backend
    -0.06
    Replace
    -0.06
     congrat
    -0.06
     initiated
    -0.06
    POSITIVE LOGITS
     thỏa
    0.06
    abal
    0.06
    elfth
    0.06
     알아
    0.06
    (Image
    0.06
    _initialized
    0.06
    :indexPath
    0.06
    .isSuccess
    0.06
    SHOT
    0.06
    コン
    0.06
    Act Density 0.047%

    No Known Activations