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

    Neuronpedia

    INDEX
    Explanations

    curly braces indicating the start of a code block or a structure in programming

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

    user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.44
    
    -0.43
    LookAnd
    -0.42
     ModelExpression
    -0.42
     تضيفلها
    -0.41
    ContentAsync
    -0.41
     المعيارى
    -0.40
     nahilalakip
    -0.39
    <bos>
    -0.38
    BASEPATH
    -0.37
    POSITIVE LOGITS
     TimeUnit
    0.56
     grat
    0.49
     Medications
    0.48
    Моло
    0.48
     Jel
    0.47
     Drug
    0.46
     TIR
    0.45
     Моло
    0.45
     caufe
    0.45
    Grat
    0.44
    Act Density 0.049%

    No Known Activations