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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron fires on comparative adjectives (words like “greater,” “higher,” “smaller,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Entity
    -0.07
     pdf
    -0.07
    정부
    -0.06
    avn
    -0.06
    工具
    -0.06
     Mapping
    -0.06
     Garner
    -0.06
     illegal
    -0.06
     mathematics
    -0.06
     API
    -0.06
    POSITIVE LOGITS
    .'</
    0.07
    owment
    0.06
    "+
    0.06
     Distance
    0.06
    ?>"/>↵
    0.06
    toBeInTheDocument
    0.06
    -details
    0.06
    <Vec
    0.06
     někter
    0.06
    ',$
    0.06
    Act Density 0.246%

    No Known Activations