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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dust
    -0.06
     ink
    -0.06
     flame
    -0.06
    	task
    -0.06
    orex
    -0.06
     accelerator
    -0.06
     distinct
    -0.06
     sockaddr
    -0.06
     auto
    -0.06
     consumed
    -0.06
    POSITIVE LOGITS
     GB
    0.06
    }↵↵
    0.06
     baj
    0.06
    DDR
    0.06
     Mathematic
    0.06
    forgettable
    0.06
    Cover
    0.06
    Mountain
    0.06
    Family
    0.06
     forestry
    0.06
    Act Density 0.007%

    No Known Activations