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

    Neuronpedia

    INDEX
    Explanations

    first and third person pronouns, often with a verb

    oai_token-act-pair · gemini-2.0-flash

    Incomplete sentence fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acağına
    -0.36
    !
    -0.35
    <h5>
    -0.35
    sa
    -0.34
    We
    -0.32
     "
    -0.32
    Even
    -0.32
    <h1>
    -0.32
    Pros
    -0.32
    .
    -0.31
    POSITIVE LOGITS
    __":
    0.91
     EconPapers
    0.91
    脚注の使い方
    0.84
    Personendaten
    0.83
    хьтан
    0.83
     الرياضيه
    0.81
     فريبيس
    0.79
     correctes
    0.78
     arşivlendi
    0.74
     HasFactory
    0.73
    Act Density 1.303%

    No Known Activations