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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    怼
    -0.07
    不开
    -0.07
    temp
    -0.07
    основ
    -0.07
     knots
    -0.07
    تكون
    -0.07
    纫
    -0.07
     operates
    -0.07
    izziness
    -0.07
    TO
    -0.06
    POSITIVE LOGITS
     никогда
    0.08
     setId
    0.08
    	Il
    0.07
     Mediterr
    0.07
    (robot
    0.07
    .Deep
    0.07
    ℳ
    0.07
    	id
    0.07
    .Fl
    0.07
     xhr
    0.07
    Act Density 0.027%

    No Known Activations