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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations or authors in scientific literature

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

    et al. citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.40
     nahilalakip
    -0.39
    awtextra
    -0.39
     "-";
    -0.37
    Translatef
    -0.35
     وتسجيلات
    -0.35
    WriteTagHelper
    -0.35
    IUrlHelper
    -0.35
    glBegin
    -0.34
     Chwiliwch
    -0.33
    POSITIVE LOGITS
     صوتيه
    0.61
     تانيه
    0.59
    transQ
    0.55
    ParallelGroup
    0.53
     etc
    0.50
     nightmares
    0.49
     hallucinations
    0.47
     graveyard
    0.46
    resaid
    0.46
    itative
    0.46
    Act Density 0.231%

    No Known Activations