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

    Neuronpedia

    INDEX
    Explanations

    patterns/trends

    np_max-act · gemini-2.0-flash

    This neuron never fires (all activations are zero), indicating it does not respond to any particular token or pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Cost
    -0.07
     rotates
    -0.07
    وید
    -0.06
    Crypt
    -0.06
    Sources
    -0.06
     cumshot
    -0.06
    iable
    -0.06
     mát
    -0.06
     Kills
    -0.06
    Gratis
    -0.06
    POSITIVE LOGITS
    <&
    0.07
     アイ
    0.06
    .single
    0.06
            ↵        ↵
    0.06
     imb
    0.06
    846
    0.06
     patterns
    0.06
    +"\
    0.06
     للإ
    0.06
     '*
    0.06
    Act Density 0.025%

    No Known Activations