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

    Neuronpedia

    INDEX
    Explanations

    question/answer pairs.

    oai_token-act-pair · gemini-2.0-flash

    yes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thâu
    -0.56
     AssemblyProduct
    -0.53
    anía
    -0.48
    ınca
    -0.46
     faute
    -0.46
    chevêque
    -0.46
    /*---
    -0.44
     виправивши
    -0.44
    apore
    -0.44
     fon
    -0.43
    POSITIVE LOGITS
     yes
    3.30
     Yes
    2.94
    Yes
    2.81
     YES
    2.70
    yes
    2.69
    YES
    2.42
     yeah
    2.20
     Yeah
    2.00
     oui
    1.85
     yep
    1.85
    Act Density 4.197%

    No Known Activations