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

    Neuronpedia

    INDEX
    Explanations

    context-specific keywords with varied meanings depending on the subject

    oai_token-act-pair · gemini-2.0-flash

    verbs related to actions and processes

    np_token-act-pair-logits · gpt-4o-mini

    the ending -ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yapılır
    -0.40
    경
    -0.40
    úb
    -0.39
     değişik
    -0.38
    beo
    -0.35
    ú
    -0.35
     kullanılır
    -0.34
    起きた
    -0.34
     maka
    -0.34
     sağlar
    -0.34
    POSITIVE LOGITS
     giving
    1.66
     providing
    1.57
     ensuring
    1.52
     making
    1.52
     bringing
    1.48
     creating
    1.46
     causing
    1.45
     demonstrating
    1.45
     proving
    1.45
     showing
    1.42
    Act Density 5.539%

    No Known Activations