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

    Neuronpedia

    INDEX
    Explanations

    instances of modal verbs indicating ability or possibility

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

    can't or can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     use
    -0.38
     tersebut
    -0.36
     itself
    -0.35
    y
    -0.35
     to
    -0.34
    as
    -0.34
     The
    -0.34
    分ほど
    -0.34
      
    -0.33
    /
    -0.32
    POSITIVE LOGITS
    <unused43>
    1.02
    <unused42>
    1.02
    <unused28>
    1.02
    <unused41>
    1.02
    <unused3>
    1.02
    [@BOS@]
    1.02
    <unused8>
    1.02
    <unused16>
    1.02
    <unused47>
    1.02
    <unused52>
    1.02
    Act Density 0.029%

    No Known Activations