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

    Neuronpedia

    INDEX
    Explanations

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demonstrators
    -0.29
     demonstration
    -0.27
     demonstrations
    -0.27
    à¹Ģว
    -0.27
    æ¼Ķ示
    -0.26
    èĦ±
    -0.25
     rewind
    -0.25
     Fior
    -0.24
    èĦ«
    -0.24
    dehyde
    -0.24
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.32
    åīįéĢĶ
    0.30
    _TYPEDEF
    0.27
    è§Ĵ度çľĭ
    0.25
    é³IJ
    0.25
    beam
    0.25
     tumor
    0.24
    eva
    0.24
    .Mutable
    0.24
    å¼Ģåıij
    0.24
    Act Density 1.027%

    No Known Activations