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

    Neuronpedia

    INDEX
    Explanations

    reactive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .beh
    -0.28
    rys
    -0.27
    FP
    -0.27
    Behavior
    -0.27
     behavior
    -0.27
    leh
    -0.26
     Occup
    -0.25
    rc
    -0.25
     under
    -0.24
    å¼Ģåıij
    -0.24
    POSITIVE LOGITS
    æĪij羣çļĦ
    0.30
    ä¹ĭä½ľ
    0.30
    ÑĪа
    0.29
    errat
    0.28
     retro
    0.28
    ffa
    0.27
    ä¸įåIJĥ
    0.27
    çļĦåĨ³å¿ĥ
    0.26
    agna
    0.26
    .bat
    0.26
    Act Density 0.016%

    No Known Activations