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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric expressions (digits, especially numbers with decimals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    είς
    -0.07
     dítě
    -0.07
     curse
    -0.06
    	Main
    -0.06
     undue
    -0.06
     hỗn
    -0.06
    .SplitContainer
    -0.06
     элем
    -0.06
    addle
    -0.06
    qm
    -0.06
    POSITIVE LOGITS
    "encoding
    0.07
     passing
    0.06
     leer
    0.06
    ,copy
    0.06
     Populate
    0.06
    oenix
    0.06
     Prop
    0.06
     streams
    0.06
     monsters
    0.06
    (connect
    0.06
    Act Density 0.074%

    No Known Activations