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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ranking
    -0.07
     примерно
    -0.06
    Aliases
    -0.06
    Một
    -0.06
     важно
    -0.06
    最后
    -0.06
    _relationship
    -0.06
    digest
    -0.06
     dünyanın
    -0.06
    .Bool
    -0.06
    POSITIVE LOGITS
    stvo
    0.06
    	Intent
    0.06
    (Block
    0.06
    romium
    0.06
     Module
    0.06
    화
    0.06
    _completed
    0.06
     isc
    0.06
    ації
    0.06
     desc
    0.06
    Act Density 0.044%

    No Known Activations