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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getCode
    -0.07
    _fun
    -0.07
    Thr
    -0.07
     które
    -0.06
    .ot
    -0.06
     миним
    -0.06
    	typedef
    -0.06
    LBL
    -0.06
    엔
    -0.06
     Idol
    -0.06
    POSITIVE LOGITS
     구글상위
    0.07
    ask
    0.06
    alore
    0.06
    levision
    0.06
    had
    0.06
     přest
    0.06
    aring
    0.06
     Palmer
    0.06
    昇
    0.06
    latent
    0.06
    Act Density 0.000%

    No Known Activations