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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to numerical data and measurements

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

    numerical features, regression problems, adult population

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     un
    -0.44
     Bar
    -0.41
     Age
    -0.40
     Ca
    -0.40
    Composable
    -0.39
     St
    -0.38
     excellent
    -0.38
     H
    -0.38
     in
    -0.37
     Pa
    -0.37
    POSITIVE LOGITS
    Geplaatst
    0.68
    InjectAttribute
    0.62
    GOTREF
    0.58
     Italijanski
    0.56
     esternos
    0.54
    IPAC
    0.54
     незавершена
    0.54
     propOrder
    0.52
    DockStyle
    0.52
     <<<<<<<<<<<<<<
    0.52
    Act Density 0.155%

    No Known Activations