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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data or measurements

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

    statistical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '))
    -0.39
     Meanwhile
    -0.39
    KommentareTeilen
    -0.37
    Geographie
    -0.36
    匿名使用者
    -0.36
    `,
    -0.35
     imágen
    -0.35
    '],
    -0.34
    ()))
    -0.34
    mería
    -0.34
    POSITIVE LOGITS
    grà
    0.60
    ✨:
    0.59
    :%
    0.56
    Personendaten
    0.54
    StoryboardSegue
    0.54
    MLLoader
    0.53
    UnusedPrivate
    0.52
     kasarigan
    0.52
     Inscrivez
    0.52
    Autoritní
    0.52
    Act Density 0.144%

    No Known Activations