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

    Neuronpedia

    INDEX
    Explanations

    1 or 2

    np_max-act · gemini-2.0-flash

    mathematical expressions or operations involving powers and simplifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tron
    -0.07
     Networks
    -0.06
    zik
    -0.06
    _coef
    -0.06
    lerde
    -0.06
    α
    -0.06
     leurs
    -0.06
     keynote
    -0.06
    aviour
    -0.06
     biopsy
    -0.06
    POSITIVE LOGITS
     yağ
    0.07
    drawer
    0.06
     charg
    0.06
    	panel
    0.06
    (reason
    0.06
     VX
    0.06
    (cancel
    0.06
     Nas
    0.06
     Jackets
    0.06
    .findViewById
    0.06
    Act Density 0.002%

    No Known Activations