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

    Neuronpedia

    INDEX
    Explanations

    exists

    np_max-act · gemini-2.0-flash

    The neuron fires on formal, technical or legal‐style exposition—e.g. paragraphs that define systems or terms, give precise specifications or instructions in academic or legal texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .projects
    -0.06
    olland
    -0.06
    รรม
    -0.06
    ninger
    -0.06
     Protect
    -0.06
     stash
    -0.06
    лада
    -0.06
    �
    -0.06
     controversy
    -0.06
    adopt
    -0.06
    POSITIVE LOGITS
    region
    0.07
    _cs
    0.07
    [selected
    0.07
    fdf
    0.07
    /full
    0.07
    functional
    0.06
    .Le
    0.06
    ()->
    0.06
     nouveaux
    0.06
    {l
    0.06
    Act Density 0.246%

    No Known Activations