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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cf
    -0.27
    Mul
    -0.25
    端æŃ£
    -0.25
     multiplication
    -0.25
    DEL
    -0.24
     Req
    -0.24
    _cf
    -0.24
    éĺ¶æ¢¯
    -0.24
    ä¹ĺ
    -0.24
    æ´ģ
    -0.24
    POSITIVE LOGITS
    éŁª
    0.26
    å°ıå§ijå¨ĺ
    0.25
    ujÄħc
    0.24
     yakın
    0.24
    erras
    0.24
     diam
    0.24
    :Is
    0.24
    igma
    0.24
    åĮĸè¿Ľç¨ĭ
    0.24
    arty
    0.24
    Act Density 0.027%

    No Known Activations