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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe quality or condition

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

    descriptive adjectives and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    };*/
    -0.42
    دانشنامهٔ
    -0.41
    ″]
    -0.41
    flute
    -0.38
    ')")
    -0.38
    RotationOrder
    -0.38
    intios
    -0.37
    dero
    -0.36
    頃の
    -0.36
     />";
    -0.36
    POSITIVE LOGITS
    SpringRunner
    0.54
    SequentialGroup
    0.52
    ########.
    0.48
    +#+#
    0.45
     defaultstate
    0.45
     increí
    0.45
     soñ
    0.45
     alcanzado
    0.43
     cortesía
    0.43
     مرئيه
    0.43
    Act Density 0.041%

    No Known Activations