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

    Neuronpedia

    INDEX
    Explanations

    gene/biomarker identification

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on floating‐point numeric values (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    OL
    -0.06
    _median
    -0.06
    _google
    -0.06
    semantic
    -0.06
     Skype
    -0.06
    readcrumb
    -0.06
     Ceramic
    -0.06
    _HIDE
    -0.06
    ective
    -0.06
    SourceType
    -0.06
    POSITIVE LOGITS
    .rs
    0.07
     Elle
    0.07
     wiel
    0.06
    phia
    0.06
     iletişim
    0.06
    .des
    0.06
    EMPLATE
    0.06
    (docs
    0.06
     tenía
    0.06
    .compute
    0.06
    Act Density 0.040%

    No Known Activations