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

    Neuronpedia

    INDEX
    Explanations

    brackets and colons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     me
    -0.08
    榜首
    -0.08
    ພ
    -0.08
     לי
    -0.08
     wt
    -0.07
    冠
    -0.07
    _GE
    -0.07
     Greater
    -0.07
    ylie
    -0.07
    总算
    -0.07
    POSITIVE LOGITS
    洪
    0.08
    Á
    0.08
     ankle
    0.07
    texto
    0.07
    ﳥ
    0.07
     musicians
    0.07
    青铜
    0.07
    ᶱ
    0.07
    Ǹ
    0.07
    水中
    0.07
    Act Density 0.005%

    No Known Activations