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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or capability

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

    "can" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    can followed by an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portály
    -0.73
    ukone
    -0.57
    vician
    -0.54
    angliski
    -0.53
    setVerticalGroup
    -0.51
    okovic
    -0.49
     ExecuteAsync
    -0.49
    arakhand
    -0.48
     fibrillation
    -0.47
    shadowOpacity
    -0.47
    POSITIVE LOGITS
     use
    0.77
     also
    0.76
    sizeCache
    0.74
    也可以
    0.67
    ]")]
    0.66
    :"-"`
    0.64
    也可
    0.63
    bilirsiniz
    0.63
     easily
    0.62
     rest
    0.61
    Act Density 0.157%

    No Known Activations