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

    Neuronpedia

    INDEX
    Explanations

    difficult

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     packs
    -0.07
     antiqu
    -0.07
    %
    -0.07
     Center
    -0.07
    β
    -0.07
     controls
    -0.06
     protection
    -0.06
     крас
    -0.06
    ycler
    -0.06
    kemiz
    -0.06
    POSITIVE LOGITS
     difficult
    0.10
     challenging
    0.07
     těž
    0.07
     ऐस
    0.07
    irs
    0.07
     tough
    0.06
     Bauer
    0.06
     difícil
    0.06
     schwer
    0.06
    .fr
    0.06
    Act Density 0.029%

    No Known Activations