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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Grid
    -0.07
     Taco
    -0.07
    .Standard
    -0.07
     запах
    -0.06
    	Server
    -0.06
     Fil
    -0.06
    parsers
    -0.06
    ril
    -0.06
    	Game
    -0.06
     UPLOAD
    -0.06
    POSITIVE LOGITS
     Raf
    0.07
     indicative
    0.06
     boyc
    0.06
     just
    0.06
    必
    0.06
    ;\
    0.06
     cleanly
    0.06
     impacts
    0.06
    �
    0.06
    �
    0.06
    Act Density 0.065%

    No Known Activations