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

    Neuronpedia

    INDEX
    Explanations

    cancellation and asynchronous operations

    np_max-act · gemini-2.0-flash

    This neuron detects references to a Boolean “IsAlive” (e.g. componentIsAlive) flag in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     block
    -0.06
    Voltage
    -0.06
    _APP
    -0.06
     Loader
    -0.06
     Alien
    -0.06
    Date
    -0.06
     gesture
    -0.06
    ymb
    -0.06
    peror
    -0.06
    omorphic
    -0.06
    POSITIVE LOGITS
     většinou
    0.07
    ترك
    0.07
    uniacid
    0.07
     letra
    0.07
     واس
    0.07
    (",")↵
    0.06
    帮助
    0.06
    .grade
    0.06
    ................................
    0.06
     �
    0.06
    Act Density 0.078%

    No Known Activations