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

    Neuronpedia

    INDEX
    Explanations

    Locations and travel

    np_max-act · gemini-2.0-flash

    This neuron never activates—it does not detect any recurring token pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nhớ
    -0.06
     confuse
    -0.06
    .initState
    -0.06
    Start
    -0.06
    AppBar
    -0.06
     Thinking
    -0.06
    Roger
    -0.06
    (screen
    -0.06
     His
    -0.06
     begins
    -0.06
    POSITIVE LOGITS
    uteur
    0.06
    イク
    0.06
     corridor
    0.06
    -policy
    0.06
    olicited
    0.06
    委
    0.06
    tam
    0.06
    méně
    0.06
     allowances
    0.06
     inadequate
    0.06
    Act Density 0.029%

    No Known Activations