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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash

    The neuron strongly fires on programming‐related action words (imperative or task verbs) such as “set,” “merge,” “detects,” “combine,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    izado
    -0.06
    BIND
    -0.06
    natural
    -0.06
     Video
    -0.06
     Both
    -0.06
    inize
    -0.06
    先
    -0.06
    anticipated
    -0.06
    xz
    -0.06
     Bryan
    -0.06
    POSITIVE LOGITS
    ="'.$
    0.07
    /{$
    0.06
    ху
    0.06
    _'.$
    0.06
    ("(
    0.06
    stateParams
    0.06
     '".$_
    0.06
    ADVERTISEMENT
    0.06
     (?
    0.06
     trespass
    0.06
    Act Density 0.172%

    No Known Activations