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

    Neuronpedia

    INDEX
    Explanations

    小

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vocals
    -0.08
     Goods
    -0.08
     году
    -0.08
     hoeven
    -0.08
                   ↵
    -0.08
     разруш
    -0.08
     goods
    -0.08
     отнош
    -0.08
     Именно
    -0.07
     ग्रह
    -0.07
    POSITIVE LOGITS
     astuces
    0.10
     Tipps
    0.10
     teaser
    0.09
     TIP
    0.09
     Twitter
    0.09
     disciplinary
    0.08
    技巧
    0.08
     caution
    0.08
     �
    0.08
     dicas
    0.08
    Act Density 0.002%

    No Known Activations