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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron is triggered by code identifiers—especially camel-cased method or function names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nüfus
    -0.06
    sprintf
    -0.06
     woll
    -0.06
    �
    -0.06
    _CHANNELS
    -0.06
    єн
    -0.06
     Planned
    -0.06
    atypes
    -0.06
     Played
    -0.06
    outs
    -0.06
    POSITIVE LOGITS
     deem
    0.06
     καθ
    0.06
    elik
    0.06
    600
    0.06
     novelist
    0.06
    lou
    0.06
     Protect
    0.06
    .getHeight
    0.06
     Plugin
    0.06
     furn
    0.06
    Act Density 0.037%

    No Known Activations