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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    PHP code related to caching responses.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on array subscript accesses (e.g. occurrences of $config[…]) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     zd
    -0.06
    locked
    -0.06
    .Var
    -0.06
    iband
    -0.06
    Pu
    -0.06
    Bear
    -0.06
    stitial
    -0.06
    peater
    -0.05
    Liquid
    -0.05
     الش
    -0.05
    POSITIVE LOGITS
     FirebaseAuth
    0.07
    /autoload
    0.07
     gui
    0.06
     RCMP
    0.06
     συνέ
    0.06
     avons
    0.06
    верд
    0.06
     meticulously
    0.06
    ，如果
    0.06
    _KEYS
    0.06
    Act Density 0.015%

    No Known Activations