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

    Neuronpedia

    INDEX
    Explanations

    commander

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     규정
    -0.07
    句话
    -0.07
    既有
    -0.07
     diligence
    -0.07
    .invokeLater
    -0.07
    𝙸
    -0.07
    aldi
    -0.07
     Stra
    -0.07
    句
    -0.06
    /ca
    -0.06
    POSITIVE LOGITS
    ὑ
    0.08
    愎
    0.07
    Human
    0.07
    urile
    0.07
    帝国
    0.07
     LET
    0.07
    protocols
    0.07
    •↵↵
    0.06
    _console
    0.06
     ejemplo
    0.06
    Act Density 0.003%

    No Known Activations