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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     broadly
    -0.08
    ?("
    -0.07
     evenly
    -0.07
    上
    -0.07
    昶
    -0.07
    非常好
    -0.07
     of
    -0.07
     vase
    -0.07
     khoá
    -0.07
    官方微信
    -0.07
    POSITIVE LOGITS
    氖
    0.06
    子宫
    0.06
    有大量的
    0.06
    _ITEMS
    0.06
     Courage
    0.06
     أج
    0.06
    TimeStamp
    0.06
     ode
    0.06
    PE
    0.06
     pod
    0.06
    Act Density 0.044%

    No Known Activations