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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point number tokens (decimal literals like “0.3583984375,” “0.3125,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    zf
    -0.07
     breadcrumbs
    -0.06
     hd
    -0.06
     креп
    -0.06
    िद
    -0.06
     пон
    -0.06
    olor
    -0.06
     dvě
    -0.06
    und
    -0.06
     tribute
    -0.06
    POSITIVE LOGITS
    ğını
    0.07
     comply
    0.07
    therapy
    0.07
     spontaneously
    0.06
    投资
    0.06
    (location
    0.06
    装置
    0.06
    ्वच
    0.06
     Prior
    0.06
     vocal
    0.06
    Act Density 0.000%

    No Known Activations