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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     труд
    -0.07
    ScrollView
    -0.07
    杯
    -0.06
    ovies
    -0.06
     step
    -0.06
     Citizens
    -0.06
    929
    -0.06
    outh
    -0.06
     fri
    -0.06
     CALLBACK
    -0.06
    POSITIVE LOGITS
     legally
    0.07
    ？
    0.06
     lg
    0.06
     之
    0.06
     })();↵
    0.06
    issors
    0.06
    pes
    0.06
    iston
    0.06
     preaching
    0.06
     alive
    0.06
    Act Density 0.000%

    No Known Activations