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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions of capability or potential actions

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

    can/could/to + action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     steen
    -0.35
    žad
    -0.35
    homonymie
    -0.33
    Want
    -0.32
     vindt
    -0.31
     want
    -0.31
    want
    -0.30
     pomoci
    -0.30
     finds
    -0.30
    になる
    -0.30
    POSITIVE LOGITS
     confidently
    0.68
     finally
    0.60
    WebVitals
    0.59
    SharedCtor
    0.59
     easily
    0.58
    AutoScaleMode
    0.58
     concentrate
    0.57
     dedicate
    0.57
     devote
    0.56
    安心して
    0.54
    Act Density 0.115%

    No Known Activations