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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe intensity or degrees of quality

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

    ending in "est" or "er"

    np_acts-logits-general · gemini-2.0-flash

    comparative and superlative endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.83
    yntaxException
    -0.83
     Audiodateien
    -0.71
    basicConfig
    -0.71
     pinulongan
    -0.68
    tvguidetime
    -0.67
     незавершена
    -0.67
    MENAFN
    -0.67
    Bibliografía
    -0.66
    OGND
    -0.66
    POSITIVE LOGITS
    est
    1.91
    EST
    1.29
    er
    1.25
     enough
    1.23
    ish
    1.00
    enough
    0.96
     genug
    0.96
    ER
    0.96
    ening
    0.89
     genoeg
    0.88
    Act Density 0.189%

    No Known Activations