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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash

    The neuron detects license‐style attribution phrasing, in particular the “as the author of” acknowledgment.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    visions
    -0.07
     Дем
    -0.06
     destination
    -0.06
     Bust
    -0.06
    دید
    -0.06
    泉
    -0.06
    .firstChild
    -0.06
     chụp
    -0.06
    」（
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    hawks
    0.07
     heterogeneous
    0.07
    coef
    0.07
    aData
    0.06
    larda
    0.06
     Analyzer
    0.06
    -e
    0.06
    Average
    0.06
    aneously
    0.06
     تعداد
    0.06
    Act Density 0.003%

    No Known Activations