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

    Neuronpedia

    INDEX
    Explanations

    benefit gain

    np_max-act · gemini-2.0-flash

    The neuron activates on terms expressing advantage or improvement (e.g. “benefit,” “gain”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     دخ
    -0.07
    -desc
    -0.06
    _pass
    -0.06
     path
    -0.06
     Roberts
    -0.06
     Hector
    -0.06
    _TEMP
    -0.06
     destabil
    -0.06
     thế
    -0.06
    -neutral
    -0.06
    POSITIVE LOGITS
     ruthless
    0.07
     setResult
    0.06
     oranı
    0.06
    (mouse
    0.06
    -lnd
    0.06
    (Sub
    0.06
     приготовить
    0.06
     эконом
    0.06
     cần
    0.06
     đem
    0.06
    Act Density 0.025%

    No Known Activations