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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to numeric tokens (e.g. digits, percentages, measurements, and decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gar
    -0.07
    ili
    -0.07
    �장
    -0.07
     spirit
    -0.06
    Paris
    -0.06
     autonomous
    -0.06
    Virginia
    -0.06
    ILI
    -0.06
    安
    -0.06
     upright
    -0.06
    POSITIVE LOGITS
     Ebay
    0.07
    dn
    0.07
    .gamma
    0.06
    flate
    0.06
    _ship
    0.06
    (app
    0.06
    .drawRect
    0.06
    tsky
    0.06
    ()));
    0.06
     VMware
    0.06
    Act Density 0.022%

    No Known Activations