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

    Neuronpedia

    INDEX
    Explanations

    phrases related to capability and authority in contexts requiring decision-making

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

    "[Something] to" or describing a state

    np_acts-logits-general · gemini-2.0-flash

    state of being capable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.74
    TagMode
    -0.59
    esine
    -0.55
    mbre
    -0.54
    Parcelize
    -0.54
    CloseOperation
    -0.53
    mander
    -0.53
    וויק
    -0.52
     bought
    -0.52
     الرياضيه
    -0.52
    POSITIVE LOGITS
     capable
    0.52
    ที่จะ
    0.50
     kaldı
    0.50
     Rossini
    0.49
     prič
    0.48
     rette
    0.47
     handling
    0.46
     capables
    0.46
     adequad
    0.46
     european
    0.46
    Act Density 0.367%

    No Known Activations