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

    Neuronpedia

    INDEX
    Explanations

    errors/warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Outcome
    -0.07
     survive
    -0.07
    CID
    -0.07
    $values
    -0.07
    ※
    -0.07
    .RestController
    -0.07
     Sid
    -0.07
    ttp
    -0.07
    ầy
    -0.07
    .
↵
↵
    -0.06
    POSITIVE LOGITS
    (passport
    0.07
     fullfile
    0.07
     FE
    0.06
    rose
    0.06
     sinon
    0.06
    .transfer
    0.06
    _long
    0.06
    astype
    0.06
    /render
    0.06
     blond
    0.06
    Act Density 0.094%

    No Known Activations