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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of inquiry

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

    asking how something is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.36
    DockStyle
    -0.35
     parha
    -0.33
    iest
    -0.33
     незавершена
    -0.32
    樣子
    -0.32
     thiên
    -0.32
    -0.31
     paced
    -0.30
    المراجع
    -0.30
    POSITIVE LOGITS
     amazing
    0.63
     nice
    0.62
     fascinating
    0.59
     strange
    0.58
     exciting
    0.58
     lovely
    0.57
     weird
    0.57
     wonderful
    0.56
     beautiful
    0.56
     dare
    0.56
    Act Density 0.011%

    No Known Activations