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

    Neuronpedia

    INDEX
    Explanations

    terms related to precision and accuracy

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

    precise description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wall
    -0.60
    bootstrapcdn
    -0.58
    IContainer
    -0.55
     informée
    -0.54
    lenme
    -0.51
    ⓧ
    -0.50
    WithMany
    -0.49
     Wall
    -0.49
    WB
    -0.49
    MyApp
    -0.49
    POSITIVE LOGITS
    precise
    0.94
     Precise
    0.89
    Precise
    0.86
     precisely
    0.85
     precise
    0.83
     precisione
    0.79
     precision
    0.73
    precision
    0.71
     precis
    0.69
     Precision
    0.67
    Act Density 0.008%

    No Known Activations