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

    Neuronpedia

    INDEX
    Explanations

    Numbers involving time limits

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens that specify procedural time periods or deadlines (e.g. “30,” “90,” “one year,” as in “30 days,” “90-day period,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    284
    -0.07
     Bord
    -0.07
     revoked
    -0.07
    ASSWORD
    -0.06
    xF
    -0.06
    #+
    -0.06
    enas
    -0.06
     Kaynak
    -0.06
     theme
    -0.06
     branding
    -0.06
    POSITIVE LOGITS
     akci
    0.06
    发出
    0.06
     км
    0.06
    pictured
    0.06
    .encoder
    0.06
     Tradable
    0.06
     ऊ
    0.06
    _country
    0.06
     خلق
    0.06
    	goto
    0.06
    Act Density 0.010%

    No Known Activations