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

    Neuronpedia

    INDEX
    Explanations

    language and scientific discussion

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of shortened forms or abbreviations (e.g. “shortened,” “pseudonym”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Κα
    -0.07
     });
    -0.07
    _SD
    -0.07
    انگلیسی
    -0.06
     �
    -0.06
     tattoo
    -0.06
    thora
    -0.06
    esity
    -0.06
    цо
    -0.06
    vection
    -0.06
    POSITIVE LOGITS
    ocoa
    0.07
    ===
    0.06
    /comment
    0.06
    memberof
    0.06
     isEqualToString
    0.06
    هاي
    0.06
     stocked
    0.06
    TARGET
    0.06
     Eag
    0.06
     grew
    0.06
    Act Density 0.137%

    No Known Activations