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

    Neuronpedia

    INDEX
    Explanations

    novel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drivers
    -0.07
    aus
    -0.06
     spawn
    -0.06
    _models
    -0.06
    ičky
    -0.06
    .Me
    -0.06
     Basement
    -0.06
    pered
    -0.06
     doorway
    -0.06
     あ
    -0.06
    POSITIVE LOGITS
     expressed
    0.06
     telah
    0.06
    staticmethod
    0.06
     vbox
    0.06
     Belg
    0.06
    knowledge
    0.06
     آسیاب
    0.06
     法
    0.06
     alk
    0.06
     secretion
    0.06
    Act Density 0.001%

    No Known Activations