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

    Neuronpedia

    INDEX
    Explanations

    words that are used to express agreement, affirmation, or support for something

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.96
    脚注の使い方
    -0.88
     виправивши
    -0.84
    ########.
    -0.83
     الحره
    -0.75
    RegressionTest
    -0.73
    issory
    -0.71
     otomatig
    -0.70
     MainAxisSize
    -0.69
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
     picture
    0.42
    мест
    0.41
    zungs
    0.40
     perfection
    0.40
    மாக
    0.39
    全力
    0.39
     currentIndex
    0.38
     vollständige
    0.38
    picture
    0.37
    za
    0.36
    Act Density 1.787%

    No Known Activations