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

    Neuronpedia

    INDEX
    Explanations

    thermodynamics/dynamics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĶ¶èİ·
    -0.30
    稼
    -0.25
    imest
    -0.25
    å¥ī
    -0.24
    iman
    -0.24
    UNC
    -0.24
    温
    -0.24
    éĢħ
    -0.23
    ä½ĥ
    -0.23
     dm
    -0.23
    POSITIVE LOGITS
    titles
    0.27
    ynchronized
    0.26
    ä¿Ŀ
    0.25
    Title
    0.25
    tank
    0.24
    尾巴
    0.23
    uki
    0.23
    Titles
    0.23
    tot
    0.23
     Tail
    0.23
    Act Density 4.754%

    No Known Activations