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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash

    That neuron fires on numeric literals containing a decimal point (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thân
    -0.06
     faces
    -0.06
    	cf
    -0.06
    -hand
    -0.06
    조
    -0.06
    děl
    -0.06
     bip
    -0.06
     Tate
    -0.06
     Страна
    -0.06
     Já
    -0.06
    POSITIVE LOGITS
    [msg
    0.07
    .sc
    0.07
    .Payment
    0.06
     defaultdict
    0.06
    clarsimp
    0.06
    thank
    0.06
     sayf
    0.06
     objected
    0.06
    _ui
    0.06
    <!--[
    0.06
    Act Density 0.083%

    No Known Activations