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

    Neuronpedia

    INDEX
    Explanations

    phrases about the potential or capability to achieve something

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

    best you can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.53
     itſelf
    -0.52
    libatkan
    -0.49
    berdayakan
    -0.44
     invokingState
    -0.42
     Autorisations
    -0.42
     igång
    -0.40
    ViewImports
    -0.39
     Autorizaciones
    -0.39
    TypedDataSet
    -0.39
    POSITIVE LOGITS
    참고
    0.56
     approximations
    0.49
     estimates
    0.49
     attempt
    0.49
     Estimates
    0.47
     للمعارف
    0.47
     attempted
    0.46
     attemp
    0.46
     approximation
    0.46
     attempts
    0.46
    Act Density 0.023%

    No Known Activations