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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or ability

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

    can or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFFIC
    -0.40
    ^@
    -0.40
    skrift
    -0.38
    orithmic
    -0.37
    haltung
    -0.37
    StructEnd
    -0.37
     olivat
    -0.36
    ậc
    -0.35
     handleSubmit
    -0.35
    全新的
    -0.35
    POSITIVE LOGITS
     puede
    1.27
     pode
    1.24
     peut
    1.21
     può
    1.18
     Puede
    1.13
    Puede
    1.12
     may
    1.09
     Peut
    1.07
    puede
    1.04
     podem
    1.02
    Act Density 0.001%

    No Known Activations