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

    Neuronpedia

    INDEX
    Explanations

    international cinema

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    货
    -0.07
    rances
    -0.07
    湖
    -0.06
    colors
    -0.06
     heartbeat
    -0.06
    ції
    -0.06
    _finish
    -0.06
     Utility
    -0.06
    	async
    -0.06
    (handler
    -0.06
    POSITIVE LOGITS
     mango
    0.07
     Planned
    0.06
     histoire
    0.06
    /gui
    0.06
     storing
    0.06
    sono
    0.06
    _off
    0.06
    .Toast
    0.06
    _RETRY
    0.06
     стари
    0.05
    Act Density 0.034%

    No Known Activations