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

    Neuronpedia

    INDEX
    Explanations

    repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aries
    -0.07
    ュー
    -0.07
     Codec
    -0.07
     الاج
    -0.06
     menu
    -0.06
     όταν
    -0.06
     Sex
    -0.06
    $obj
    -0.06
    .connected
    -0.06
     password
    -0.06
    POSITIVE LOGITS
     deja
    0.07
    .Unmarshal
    0.07
     requiring
    0.06
     него
    0.06
     luckily
    0.06
     evidently
    0.06
    搞
    0.06
     تصویر
    0.06
     dealt
    0.06
    dashboard
    0.06
    Act Density 0.010%

    No Known Activations