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

    Neuronpedia

    INDEX
    Explanations

    flux

    np_max-act · gemini-2.0-flash

    The neuron responds primarily to longer, multi-syllabic content words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ullo
    -0.06
     into
    -0.06
     marathon
    -0.06
    _DAMAGE
    -0.06
     tmp
    -0.06
    .parallel
    -0.06
    ..."↵↵
    -0.06
    ивши
    -0.06
    !!↵
    -0.06
    ebo
    -0.06
    POSITIVE LOGITS
    .ASCII
    0.06
    _REF
    0.06
     då
    0.06
     HDF
    0.06
    clared
    0.06
     pornost
    0.06
     FTC
    0.06
     работе
    0.06
    /find
    0.06
     Hacker
    0.06
    Act Density 0.318%

    No Known Activations