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

    Neuronpedia

    INDEX
    Explanations

    Code and emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Framework
    -0.07
    _tweet
    -0.06
    格式
    -0.06
     knocked
    -0.06
    every
    -0.06
    CallBack
    -0.06
    Team
    -0.06
    terror
    -0.06
    n
    -0.06
     defendant
    -0.06
    POSITIVE LOGITS
    ิบ
    0.07
     mỹ
    0.06
    /User
    0.06
     SIMD
    0.06
     CIT
    0.06
     mast
    0.06
    mad
    0.06
    -save
    0.06
     khí
    0.06
     phù
    0.06
    Act Density 0.015%

    No Known Activations