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

    Neuronpedia

    INDEX
    Explanations

    code comparison operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tele
    -0.07
    Emitter
    -0.06
    енд
    -0.06
    词
    -0.06
     arrayWith
    -0.06
    ICE
    -0.06
    áy
    -0.06
     XIII
    -0.06
    	Log
    -0.06
    lamp
    -0.06
    POSITIVE LOGITS
     cooking
    0.07
     смот
    0.07
     jmen
    0.06
     incurred
    0.06
     voting
    0.06
     personally
    0.06
     Parent
    0.06
     encontr
    0.06
     afect
    0.06
     M
    0.06
    Act Density 0.013%

    No Known Activations