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

    Neuronpedia

    INDEX
    Explanations

    references to software libraries and modules

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

    user input lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.66
    utilisons
    -0.54
     <>",
    -0.51
     eenige
    -0.51
     Савезне
    -0.50
     afgelopen
    -0.50
    OGND
    -0.46
    oredCriteria
    -0.46
     Мексичка
    -0.44
     enfans
    -0.42
    POSITIVE LOGITS
     Arts
    0.69
     arts
    0.66
     Fantasia
    0.64
     MPC
    0.63
    arts
    0.63
     cuisine
    0.61
     Economy
    0.61
    seu
    0.60
     Identity
    0.59
     Artis
    0.59
    Act Density 0.002%

    No Known Activations