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

    Neuronpedia

    INDEX
    Explanations

    terms related to accuracy and precision

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

    accuracy or precision

    np_acts-logits-general · gemini-2.0-flash

    accuracy and precision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.47
    LookAnd
    -0.43
     KI
    -0.43
    WB
    -0.39
     /\.
    -0.37
    CardHeader
    -0.36
    CppCodeGen
    -0.36
     pul
    -0.35
     Duk
    -0.35
     openly
    -0.35
    POSITIVE LOGITS
     Accurate
    0.80
    Accurate
    0.79
     ACCUR
    0.78
     Exacts
    0.77
     accuracy
    0.77
    precise
    0.77
    Precision
    0.75
     precisione
    0.75
     Exactos
    0.75
     precision
    0.74
    Act Density 0.212%

    No Known Activations