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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_max-act · gemini-2.0-flash

    The neuron is triggered by numerical tokens, especially floating-point numbers with decimal points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     symbols
    -0.07
     čist
    -0.06
     Chen
    -0.06
    디오
    -0.06
     Prod
    -0.06
    िद
    -0.06
    selectAll
    -0.06
    parcel
    -0.06
     shed
    -0.06
     genomes
    -0.06
    POSITIVE LOGITS
    \C
    0.07
    +-
    0.06
    价
    0.06
     SSL
    0.06
    ={'
    0.06
     ($('#
    0.06
     Pru
    0.06
     SMALL
    0.06
    Normalization
    0.06
    .Mark
    0.06
    Act Density 0.009%

    No Known Activations