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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron is effectively dead—it never activates on any text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _hour
    -0.07
    .ImageView
    -0.06
    .strptime
    -0.06
    .words
    -0.06
     pep
    -0.06
    FromDate
    -0.06
    ์
    -0.06
    .od
    -0.06
     toc
    -0.06
    _j
    -0.06
    POSITIVE LOGITS
     SDL
    0.07
     stdin
    0.06
    ADB
    0.06
     `↵
    0.06
     Wrong
    0.06
    _flat
    0.06
     lista
    0.06
    Log
    0.06
     Need
    0.06
     famously
    0.06
    Act Density 0.003%

    No Known Activations