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

    Neuronpedia

    INDEX
    Explanations

    Customer satisfaction surveys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ดา
    -0.07
     pornôs
    -0.06
     Materials
    -0.06
    reak
    -0.06
     Specs
    -0.06
    GU
    -0.06
    КА
    -0.06
    重点
    -0.06
     PIX
    -0.06
     Top
    -0.05
    POSITIVE LOGITS
    (Conv
    0.07
     tagging
    0.07
     contador
    0.06
    .cid
    0.06
     různých
    0.06
    	expected
    0.06
     improvement
    0.06
     много
    0.06
     depressive
    0.06
     numel
    0.06
    Act Density 0.003%

    No Known Activations