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

    Neuronpedia

    INDEX
    Explanations

    ||

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical data entries (scores, table statistics, and other numbers) typically found in sports‐style standings or results tables.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    AIT
    -0.06
    atives
    -0.06
    _delay
    -0.06
    _DOT
    -0.06
    Elapsed
    -0.06
    ':
    -0.06
    914
    -0.06
    ysl
    -0.06
    Sl
    -0.06
    Deleting
    -0.06
    POSITIVE LOGITS
     ظرفیت
    0.07
     التح
    0.07
    цик
    0.07
    ูก
    0.07
     баз
    0.06
     PdfP
    0.06
     Recursive
    0.06
     olası
    0.06
    achievement
    0.06
    aden
    0.06
    Act Density 0.009%

    No Known Activations