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

    Neuronpedia

    INDEX
    Explanations

    terms related to electrical power systems and components

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

    Follows numbers, punctuation, or fragments

    np_acts-logits-general · gemini-2.0-flash

    compound nouns and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     things
    -0.60
     whatnot
    -0.53
    mybatisplus
    -0.51
    raisemb
    -0.51
     Theſe
    -0.50
     THINGS
    -0.50
     unsustainable
    -0.50
     Reck
    -0.49
     Things
    -0.49
     Failing
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.72
     opcional
    0.70
     optional
    0.68
     optionally
    0.63
    alyptus
    0.63
    optional
    0.62
     Optional
    0.61
     fully
    0.61
     있어
    0.60
    Optional
    0.60
    Act Density 0.296%

    No Known Activations