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

    Neuronpedia

    INDEX
    Explanations

    Mah

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    输
    -0.08
    dfd
    -0.07
    <Member
    -0.07
     dusty
    -0.07
    mtx
    -0.07
    ờ
    -0.07
     calloc
    -0.07
    (fake
    -0.07
    ﳋ
    -0.07
    🄽
    -0.07
    POSITIVE LOGITS
    きれい
    0.08
     pleasant
    0.07
    充值
    0.07
    =#{
    0.07
    年末
    0.07
     бесплат
    0.07
    嫫
    0.07
     Lounge
    0.07
    office
    0.07
    Inicial
    0.07
    Act Density 0.001%

    No Known Activations