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

    Neuronpedia

    INDEX
    Explanations

    Commons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пут
    -0.07
     jas
    -0.06
    .nasa
    -0.06
     nhu
    -0.06
     maneuver
    -0.06
    menin
    -0.06
    .ot
    -0.06
    .setLayout
    -0.06
     Opt
    -0.06
    anax
    -0.06
    POSITIVE LOGITS
     Commons
    0.08
    	dis
    0.07
     doctors
    0.07
    ес
    0.06
     mortgage
    0.06
     Incredible
    0.06
    bd
    0.06
    ns
    0.06
     prices
    0.06
    (strings
    0.06
    Act Density 0.000%

    No Known Activations