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

    Neuronpedia

    INDEX
    Explanations

    error messages

    np_max-act · gemini-2.0-flash

    technical language related to programming and software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ーズ
    -0.07
     Higher
    -0.06
     Werk
    -0.06
    Params
    -0.06
     drills
    -0.06
    samples
    -0.06
    hur
    -0.06
    青
    -0.06
    fuck
    -0.06
    UIAlertAction
    -0.06
    POSITIVE LOGITS
     LAT
    0.07
    ина
    0.07
    liğinde
    0.06
    acement
    0.06
    innacle
    0.06
     lia
    0.06
    intptr
    0.06
     devez
    0.06
    getClass
    0.06
    ANDOM
    0.06
    Act Density 0.011%

    No Known Activations