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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash

    This neuron never fires—it does not reliably activate on any visible token or pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    芙
    -0.07
    sek
    -0.07
     addSubview
    -0.06
     Gy
    -0.06
    _group
    -0.06
     películ
    -0.06
    	label
    -0.06
    matches
    -0.06
    UIAlert
    -0.06
    Reports
    -0.06
    POSITIVE LOGITS
     öldür
    0.07
    (ct
    0.07
    收
    0.06
    consume
    0.06
     Geile
    0.06
     Explosion
    0.06
     hiểm
    0.06
     PROC
    0.06
     收
    0.06
    Repeated
    0.06
    Act Density 0.002%

    No Known Activations