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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens that are floating‐point (i.e. decimal) values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    medical terminology related to immune responses and diseases.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     церкви
    -0.07
    ázal
    -0.07
     PAD
    -0.07
    iset
    -0.07
    ,target
    -0.06
    _sidebar
    -0.06
    _NO
    -0.06
     existe
    -0.06
    lanmıştır
    -0.06
     روستا
    -0.06
    POSITIVE LOGITS
    (score
    0.07
    ması
    0.06
     erm
    0.06
    .Lookup
    0.06
    poll
    0.06
    (chain
    0.06
    hue
    0.06
    (dm
    0.06
    _PROF
    0.06
     SELF
    0.06
    Act Density 0.101%

    No Known Activations