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

    Neuronpedia

    INDEX
    Explanations

    approximate quantities or measurements

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

    approximation

    np_acts-logits-general · gemini-2.0-flash

    approximations of quantities and monetary values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     przecież
    -0.45
     pourtant
    -0.42
     nemlig
    -0.39
    resave
    -0.37
    even
    -0.36
     навіть
    -0.35
    ďaka
    -0.34
     дори
    -0.34
     uyar
    -0.34
    antd
    -0.33
    POSITIVE LOGITS
     ungefähr
    0.85
     approximately
    0.83
     approximate
    0.82
     approx
    0.81
     Approximately
    0.79
     approximates
    0.79
    Approx
    0.79
     aproximadamente
    0.78
     Approx
    0.77
     aproximado
    0.77
    Act Density 0.398%

    No Known Activations