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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or evaluative adjectives that convey strong emotional states

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

    ending in "en" or "ening"

    np_acts-logits-general · gemini-2.0-flash

    adjective root + en/ens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.85
     تانيه
    -0.84
    oa̍t
    -0.84
    yntaxException
    -0.84
    ècie
    -0.83
    :✨
    -0.80
    Portale
    -0.80
    -0.76
     GeoNames
    -0.75
    Tikang
    -0.74
    POSITIVE LOGITS
    ening
    1.71
    ened
    1.58
    ENING
    1.21
    ENED
    1.19
    ener
    1.07
    ens
    1.01
    eners
    0.83
    en
    0.82
    ENS
    0.72
    le
    0.72
    Act Density 0.195%

    No Known Activations