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

    Neuronpedia

    INDEX
    Explanations

    domains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arena
    -0.07
    .queue
    -0.07
     lick
    -0.07
    郭
    -0.06
    records
    -0.06
     iron
    -0.06
    	direction
    -0.06
     flux
    -0.06
     flips
    -0.06
     Nir
    -0.06
    POSITIVE LOGITS
    ância
    0.07
    .sdk
    0.07
     CONSEQUENTIAL
    0.07
     khả
    0.06
     националь
    0.06
     plunged
    0.06
    uetype
    0.06
    ท
    0.06
    ผล
    0.06
    .addTab
    0.06
    Act Density 0.008%

    No Known Activations