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

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /app
    -0.07
     orbital
    -0.07
    ore
    -0.07
    	max
    -0.06
    ули
    -0.06
    istrat
    -0.06
     hierarchical
    -0.06
    ulis
    -0.06
     mayor
    -0.06
    Rs
    -0.06
    POSITIVE LOGITS
    하면서
    0.06
     miệng
    0.06
     mezi
    0.06
    classic
    0.06
     bakış
    0.06
    組織
    0.06
     تومان
    0.06
    ’nun
    0.06
     наших
    0.06
     листь
    0.06
    Act Density 0.060%

    No Known Activations