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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potential actions or possibilities

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

    Following "can" or "could"

    np_acts-logits-general · gemini-2.0-flash

    can/could followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ctools
    -0.56
    StoryboardSegue
    -0.53
    VIAF
    -0.51
     the
    -0.49
     ugy
    -0.48
    новништво
    -0.48
    mtable
    -0.48
    期刊论文
    -0.47
     these
    -0.46
     Hunt
    -0.46
    POSITIVE LOGITS
    setViewportView
    0.61
    ThroughAttribute
    0.61
    EDEFAULT
    0.59
    INSEE
    0.56
    notated
    0.56
    Bakgrunnsstoff
    0.55
    tvguidetime
    0.55
    السكان
    0.54
    częściej
    0.53
    Rujuakan
    0.51
    Act Density 0.185%

    No Known Activations