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

    Neuronpedia

    INDEX
    Explanations

    SHA

    np_max-act · gemini-2.0-flash

    The neuron fires on references to SHA‐based hashing algorithms (e.g. tokens like “sha1,” “sha256,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Eins
    -0.08
     RTS
    -0.07
     Lionel
    -0.07
    FFFFFF
    -0.07
     Palmer
    -0.06
     yeast
    -0.06
    ickt
    -0.06
    paint
    -0.06
     Nail
    -0.06
    wjgl
    -0.06
    POSITIVE LOGITS
     ihtiyaç
    0.07
    .sha
    0.07
     belirtilen
    0.07
    multiple
    0.07
     tablespoon
    0.07
    рою
    0.07
    ================
    0.06
     soo
    0.06
     oblivious
    0.06
    .ForeignKey
    0.06
    Act Density 0.002%

    No Known Activations