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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing decimal values (i.e., floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    old
    -0.07
    0
    -0.07
     Ive
    -0.07
    ms
    -0.06
    yd
    -0.06
     ing
    -0.06
    .nom
    -0.06
    -card
    -0.06
     Suff
    -0.06
    xed
    -0.06
    POSITIVE LOGITS
     between
    0.20
     Between
    0.17
    between
    0.15
    Between
    0.13
     BETWEEN
    0.12
     tussen
    0.12
    -between
    0.11
     zwischen
    0.10
    _between
    0.10
     beneath
    0.09
    Act Density 0.061%

    No Known Activations