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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urf
    -0.07
    の
    -0.06
     зб
    -0.06
    DataRow
    -0.06
     nhiệm
    -0.06
    �
    -0.06
    oeff
    -0.06
     الآ
    -0.06
     wk
    -0.06
    แกรม
    -0.06
    POSITIVE LOGITS
     RECEIVER
    0.07
    /__
    0.06
     Lever
    0.06
     naive
    0.06
     forward
    0.06
    alesce
    0.06
    ाहर
    0.06
     Appl
    0.06
    様
    0.06
    eature
    0.06
    Act Density 0.001%

    No Known Activations