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

    Neuronpedia

    INDEX
    Explanations

    seeing

    np_max-act · gemini-2.0-flash

    computational and technical references regarding AI training and resources.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric tokens containing a decimal point.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iPad
    -0.06
    _ORIGIN
    -0.06
    Download
    -0.06
     Winner
    -0.06
     mornings
    -0.06
    ovanou
    -0.06
    -Men
    -0.06
     输入
    -0.06
     루
    -0.06
    Dev
    -0.06
    POSITIVE LOGITS
    uncan
    0.07
     assim
    0.06
    ิจารณ
    0.06
     whites
    0.06
    imité
    0.06
    .shuffle
    0.06
    zelf
    0.06
    roots
    0.06
    èle
    0.05
    ////////////////////////////////////////////////////////////////
    0.05
    Act Density 0.381%

    No Known Activations