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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legal terms and proceedings

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

    that end in certain suffixes

    np_acts-logits-general · gemini-2.0-flash

    completing known prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ena
    -0.41
    ane
    -0.40
    ida
    -0.38
    ick
    -0.37
    chery
    -0.36
    inas
    -0.36
    cken
    -0.36
     nakalista
    -0.36
    kian
    -0.36
    ys
    -0.36
    POSITIVE LOGITS
     början
    0.34
    berdayakan
    0.33
     stället
    0.32
     igång
    0.30
    harapkan
    0.30
     före
    0.30
     vocales
    0.29
     felicitación
    0.29
    excess
    0.29
     fuerzas
    0.29
    Act Density 2.636%

    No Known Activations