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

    Neuronpedia

    INDEX
    Explanations

    Height

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (digits and measurement figures), especially in physical‐stat measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Porno
    -0.07
    'B
    -0.07
     newer
    -0.06
     Olympics
    -0.06
     dissoci
    -0.06
    	attr
    -0.06
     dann
    -0.06
     soil
    -0.06
     scant
    -0.06
    έ
    -0.06
    POSITIVE LOGITS
    .")]↵
    0.07
     何
    0.07
     gravel
    0.06
    Sym
    0.06
    vik
    0.06
     هدف
    0.06
    Stay
    0.06
    Txt
    0.06
     ISPs
    0.06
     originate
    0.06
    Act Density 0.003%

    No Known Activations