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

    Neuronpedia

    INDEX
    Explanations

    statements involving abilities and achievements

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

    preceding "able," "can," or related terms

    np_acts-logits-general · gemini-2.0-flash

    ability to do or be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    belongs
    -0.55
    EROUS
    -0.53
    Greetings
    -0.47
    sschutz
    -0.47
    orea
    -0.47
     Spuren
    -0.46
    نامج
    -0.46
     parseFrom
    -0.46
     Bork
    -0.45
    asari
    -0.45
    POSITIVE LOGITS
     able
    1.99
     ability
    1.93
     Ability
    1.56
    Ability
    1.53
     Able
    1.43
    Able
    1.42
     capaz
    1.37
     capable
    1.32
     capaces
    1.27
     capability
    1.26
    Act Density 0.525%

    No Known Activations