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

    Neuronpedia

    INDEX
    Explanations

    tablets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (timeout
    -0.07
    NavigationBar
    -0.07
    ZF
    -0.07
    .teacher
    -0.07
    .ly
    -0.06
    ق
    -0.06
    Alloc
    -0.06
     Chan
    -0.06
    WSC
    -0.06
    vw
    -0.06
    POSITIVE LOGITS
    gatsby
    0.06
    аю
    0.06
     thiệu
    0.06
    follower
    0.06
    training
    0.06
     yourselves
    0.06
     และ
    0.06
     Geh
    0.05
    Ending
    0.05
    üsseldorf
    0.05
    Act Density 0.006%

    No Known Activations