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

    Neuronpedia

    INDEX
    Explanations

    Chrome

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of web browsers (often paired with version numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prophets
    -0.06
     onBind
    -0.06
    GD
    -0.06
    -ag
    -0.06
    أس
    -0.06
     eight
    -0.06
    .NOT
    -0.06
    982
    -0.06
    .onActivityResult
    -0.06
    eras
    -0.06
    POSITIVE LOGITS
    }↵↵↵
    0.07
    ﾆ
    0.07
     ی
    0.07
     storyt
    0.06
    (sheet
    0.06
     Tax
    0.06
     Estate
    0.06
     зазнач
    0.06
     traces
    0.06
     gerçekten
    0.06
    Act Density 0.005%

    No Known Activations