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

    Neuronpedia

    INDEX
    Explanations

    instances of opinions, thoughts, and judgements using phrases like "I think", "that we know", "that would" and "argue".

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

    np_token-act-pair-logits · gpt-4o-mini

    Expressing beliefs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.70
     سكانية
    -0.70
    ^(@)
    -0.63
    })$}
    -0.63
     crdi
    -0.63
     كومونز
    -0.60
     незавершена
    -0.60
    ynos
    -0.60
     Baillargeon
    -0.60
     ་་
    -0.59
    POSITIVE LOGITS
     is
    1.22
     has
    1.14
     will
    1.03
     would
    0.96
     was
    0.95
     are
    0.85
     represents
    0.82
     might
    0.81
     may
    0.78
     constitutes
    0.76
    Act Density 8.942%

    No Known Activations