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
     бел
    -0.07
     erfolgre
    -0.06
    막
    -0.06
     Natasha
    -0.06
     giai
    -0.06
     submarine
    -0.06
     τελευτα
    -0.06
     Ginny
    -0.06
     maior
    -0.05
    �
    -0.05
    POSITIVE LOGITS
    ัฒ
    0.08
     lateinit
    0.08
    .Configure
    0.07
     exercitation
    0.07
    xfb
    0.07
     hơi
    0.07
    /latest
    0.07
     میک
    0.07
    /
↵
    0.07
     기자
    0.07
    Act Density 0.000%

    No Known Activations