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

    Neuronpedia

    INDEX
    Explanations

    Anth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Razor
    -0.08
    .Map
    -0.07
    게임
    -0.07
    enqueue
    -0.07
     Stark
    -0.07
     folded
    -0.07
    πη
    -0.07
    ؤال
    -0.07
    While
    -0.07
    asin
    -0.07
    POSITIVE LOGITS
     Anth
    0.07
    objc
    0.06
    Anth
    0.06
     anth
    0.06
     roma
    0.06
     člověk
    0.06
     Hann
    0.05
     쿠
    0.05
    }'",
    0.05
    �
    0.05
    Act Density 0.002%

    No Known Activations