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

    Neuronpedia

    INDEX
    Explanations

    say "uthor"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仰
    -0.07
     μετα
    -0.07
    _',
    -0.07
    -rec
    -0.06
    )↵↵↵↵↵↵
    -0.06
    尘
    -0.06
    _replace
    -0.06
    овари
    -0.06
     Мат
    -0.06
    ();↵↵↵↵
    -0.06
    POSITIVE LOGITS
    jmu
    0.07
    enzyme
    0.06
    $file
    0.06
     LoginComponent
    0.06
    uvian
    0.06
     leaderboard
    0.06
    getPage
    0.06
     backgroundImage
    0.06
     řekl
    0.06
    aku
    0.06
    Act Density 0.043%

    No Known Activations