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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tahap
    -0.07
     milestones
    -0.07
     potentially
    -0.07
     tres
    -0.07
     dł
    -0.07
    ror
    -0.07
    trak
    -0.07
     environment
    -0.07
    entation
    -0.07
     suffix
    -0.07
    POSITIVE LOGITS
     specializes
    0.10
     gespecialiseerd
    0.09
    负责
    0.09
     specialising
    0.09
     specializing
    0.09
    Recently
    0.09
    formerly
    0.09
     specialise
    0.09
    以前
    0.09
     recently
    0.09
    Act Density 0.081%

    No Known Activations