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

    Neuronpedia

    INDEX
    Explanations

    detection

    np_max-act · gemini-2.0-flash

    discussions surrounding cybersecurity vulnerabilities and defenses against malicious attacks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ourselves
    -0.06
    (productId
    -0.06
    _UFunction
    -0.06
    ITCH
    -0.06
    onse
    -0.06
    _Length
    -0.06
     Practice
    -0.06
     Cargo
    -0.06
    eti
    -0.06
    17
    -0.06
    POSITIVE LOGITS
    __,↵
    0.07
     ett
    0.06
     correspondence
    0.06
     sıra
    0.06
    猫
    0.06
    xima
    0.06
     devlet
    0.06
     cest
    0.06
     О
    0.06
     mes
    0.06
    Act Density 0.030%

    No Known Activations