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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脑
    -0.07
    cw
    -0.07
     alınması
    -0.06
    ládání
    -0.06
    .operator
    -0.06
     reef
    -0.06
    leta
    -0.06
     soğuk
    -0.06
     cutter
    -0.06
     دولار
    -0.06
    POSITIVE LOGITS
     sufficiently
    0.07
    ��
    0.06
     playwright
    0.06
    젝
    0.06
    κει
    0.06
     confirmPassword
    0.06
     constituency
    0.06
     Plug
    0.06
    ování
    0.06
    ощ
    0.06
    Act Density 0.006%

    No Known Activations