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

    Neuronpedia

    INDEX
    Explanations

    application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cheer
    -0.07
    odata
    -0.07
     incentives
    -0.07
    holding
    -0.07
    zip
    -0.06
    Order
    -0.06
     emanc
    -0.06
    Bus
    -0.06
    cuts
    -0.06
    ieten
    -0.06
    POSITIVE LOGITS
    /dis
    0.06
    _SAMPLES
    0.06
     Het
    0.06
     strategically
    0.06
    惊
    0.06
     blanco
    0.06
    BuilderFactory
    0.06
    	DD
    0.06
     наш
    0.06
     BadRequest
    0.06
    Act Density 0.031%

    No Known Activations