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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lexia
    -0.65
    <bos>
    -0.64
     research
    -0.63
    HasForeignKey
    -0.61
     Research
    -0.58
    Research
    -0.57
     للمعارف
    -0.54
     himo
    -0.54
    '
    -0.52
     commitment
    -0.47
    POSITIVE LOGITS
     createState
    0.73
    seamnă
    0.66
    IntoConstraints
    0.64
    новништво
    0.59
    esercito
    0.59
    setVerticalGroup
    0.56
    Buongiorno
    0.56
    ulipas
    0.56
    日閲覧
    0.56
     battre
    0.54
    Act Density 1.463%

    No Known Activations