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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (decimal numbers with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     disemb
    -0.07
     sommes
    -0.07
     Rag
    -0.06
    uts
    -0.06
    .Addr
    -0.06
     embroidery
    -0.06
     داستان
    -0.06
     pau
    -0.06
     Pes
    -0.06
     Hakk
    -0.06
    POSITIVE LOGITS
     sở
    0.08
    (ball
    0.06
    bbing
    0.06
    -educated
    0.06
     shutting
    0.06
    VED
    0.06
    shipping
    0.06
     reconstruct
    0.06
     а
    0.06
    fade
    0.06
    Act Density 0.011%

    No Known Activations