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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and components

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

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.71
     يتيمه
    -0.71
    UrlResolution
    -0.60
     nakalista
    -0.52
    PostInfinity
    -0.50
    CROSSTALK
    -0.49
     Taktlose
    -0.48
    Espèce
    -0.48
     дописавши
    -0.47
     considérons
    -0.47
    POSITIVE LOGITS
     Scanner
    0.45
     Hello
    0.44
    Scanner
    0.38
     Trapp
    0.35
     Zapo
    0.35
    .*;
    0.34
     Mane
    0.34
     المج
    0.34
    scanner
    0.33
     hello
    0.33
    Act Density 0.003%

    No Known Activations