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

    Neuronpedia

    INDEX
    Explanations

    technical terms and symbols related to computations and programming in documents

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

    Lua programming language files

    np_acts-logits-general · gemini-2.0-flash

    names followed by years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hein
    -0.73
     Dwyer
    -0.71
     Hein
    -0.70
     Anja
    -0.67
     Cypress
    -0.67
     Miele
    -0.65
     Rosario
    -0.64
     Bart
    -0.64
     Bartlett
    -0.63
    Bart
    -0.63
    POSITIVE LOGITS
     Loth
    0.77
     Bullock
    0.75
     Hatton
    0.68
     Buxton
    0.68
     Davison
    0.66
     Horv
    0.64
     Norfolk
    0.64
     máy
    0.60
     Creighton
    0.60
     Auro
    0.59
    Act Density 0.937%

    No Known Activations