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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    The neuron activates on the single-digit issue or page numbers in journal citation strings (i.e. the digit immediately following the hyphen in a reference code).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lã
    -0.07
    -training
    -0.06
    械
    -0.06
     Providing
    -0.06
     Wheels
    -0.06
     satisfy
    -0.06
     रह
    -0.06
    �
    -0.06
    anism
    -0.06
     Rafael
    -0.06
    POSITIVE LOGITS
     omap
    0.07
    Objective
    0.07
     #'
    0.07
    -fw
    0.06
    -food
    0.06
    퍼
    0.06
    AA
    0.06
    ,,
    0.06
    ,response
    0.06
    _por
    0.06
    Act Density 0.002%

    No Known Activations