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

    Neuronpedia

    INDEX
    Explanations

    less than

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are floating‐point numbers—i.e. decimal numerals with a “.” in them.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to food and agricultural trade issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Material
    -0.07
     ramifications
    -0.07
     rever
    -0.07
    (packet
    -0.07
    Redirect
    -0.06
     renowned
    -0.06
    .Users
    -0.06
    extras
    -0.06
    Income
    -0.06
     ACCESS
    -0.06
    POSITIVE LOGITS
     nằm
    0.07
    ं
    0.06
    lobal
    0.06
    quoise
    0.06
    luluk
    0.06
     erfolgreich
    0.06
     unf
    0.06
    
    0.06
    olkata
    0.06
     yoktur
    0.06
    Act Density 0.363%

    No Known Activations