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

    Neuronpedia

    INDEX
    Explanations

    textual elements related to data structures or variables in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    buy it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hutton
    -0.81
     Whitby
    -0.69
     Dune
    -0.67
     Domen
    -0.65
     MPA
    -0.64
     Kae
    -0.62
     AMI
    -0.61
     Newmarket
    -0.61
     Kra
    -0.61
     Rack
    -0.61
    POSITIVE LOGITS
     Delgado
    0.80
     Atlas
    0.78
     Δ
    0.73
    Lew
    0.70
     Morse
    0.69
     Steele
    0.68
     Lew
    0.68
     Elvis
    0.68
     atlas
    0.67
     delta
    0.66
    Act Density 1.051%

    No Known Activations