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

    Neuronpedia

    INDEX
    Explanations

    concepts related to hypothesis formation and empirical testing

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

    testing hypotheses and theories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.52
     Италијани
    -0.49
     autorytatywna
    -0.49
    ☚
    -0.44
    ChromeDriver
    -0.44
    TintMode
    -0.42
    ViewImports
    -0.41
    ArrowToggle
    -0.41
    Chham
    -0.40
    strix
    -0.40
    POSITIVE LOGITS
    interopRequire
    0.47
     hypothesis
    0.45
    外部連結
    0.41
     contradicted
    0.39
     hypotheses
    0.38
     SUPPORT
    0.38
     unsupported
    0.38
     investigação
    0.38
     terenie
    0.38
     Hypothesis
    0.38
    Act Density 0.604%

    No Known Activations