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

    Neuronpedia

    INDEX
    Explanations

    code, configuration files

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals containing decimal points (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Czech
    -0.06
    lie
    -0.06
    referrer
    -0.06
     условия
    -0.06
     ViewState
    -0.05
     Commerce
    -0.05
    νια
    -0.05
    %%↵
    -0.05
    Possible
    -0.05
     Liberation
    -0.05
    POSITIVE LOGITS
    .Margin
    0.07
     مز
    0.07
     گردش
    0.07
     συμβ
    0.06
    <Renderer
    0.06
    536
    0.06
    址
    0.06
    -equiv
    0.06
     pouco
    0.06
     MERCHANTABILITY
    0.06
    Act Density 0.128%

    No Known Activations