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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ji
    -0.08
    라마
    -0.07
    jk
    -0.07
    >M
    -0.07
    ipeline
    -0.06
    Dados
    -0.06
    GINE
    -0.06
    伝
    -0.06
     données
    -0.06
     Howard
    -0.06
    POSITIVE LOGITS
    _weak
    0.07
     Citation
    0.06
     acquainted
    0.06
    $lang
    0.06
     astronaut
    0.06
    ])):↵
    0.06
     Bellev
    0.06
     AssemblyDescription
    0.06
     neby
    0.06
    ErrorResponse
    0.06
    Act Density 0.025%

    No Known Activations