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

    Neuronpedia

    INDEX
    Explanations

    Code/website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tr
    -0.07
     لم
    -0.07
    SKIP
    -0.07
    ☚
    -0.07
    ]");↵
    -0.06
    "</
    -0.06
    裸
    -0.06
    良好
    -0.06
     accompanying
    -0.06
    _ld
    -0.06
    POSITIVE LOGITS
     객체
    0.07
    -resource
    0.07
    .setdefault
    0.07
     Jays
    0.07
     joy
    0.07
    <?>
    0.07
    antino
    0.07
     virtues
    0.07
    rels
    0.07
    viewport
    0.07
    Act Density 0.004%

    No Known Activations