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

    Neuronpedia

    INDEX
    Explanations

    Shortage

    np_max-act · gemini-2.0-flash

    The neuron activates on passages containing quantitative data—numbers, statistics, and measurable figures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ход
    -0.07
     indirectly
    -0.06
    ulates
    -0.06
     dope
    -0.06
    вит
    -0.06
    Me
    -0.06
     sixty
    -0.06
    eth
    -0.06
     REC
    -0.06
    }];↵
    -0.06
    POSITIVE LOGITS
    |[
    0.07
    .tagName
    0.06
    setName
    0.06
    كز
    0.06
    -ul
    0.06
     muestra
    0.06
    instant
    0.06
     них
    0.06
    Aceptar
    0.06
     popcorn
    0.06
    Act Density 0.056%

    No Known Activations