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

    Neuronpedia

    INDEX
    Explanations

    array dimensions

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Save
    -0.08
     Macron
    -0.06
    Fire
    -0.06
    Silver
    -0.06
    reibung
    -0.06
     Ch
    -0.06
    ，他们
    -0.06
    Colon
    -0.06
    (customer
    -0.06
     Jill
    -0.06
    POSITIVE LOGITS
     bd
    0.06
     zaměst
    0.06
     Venue
    0.06
     başv
    0.06
    obre
    0.06
    .index
    0.06
     매
    0.06
     abb
    0.06
     appliance
    0.06
    ‐-
    0.06
    Act Density 0.013%

    No Known Activations