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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [[[
    -0.07
     факти
    -0.07
    .portal
    -0.06
    ��
    -0.06
     Helper
    -0.06
    .make
    -0.06
     ileri
    -0.06
    主任
    -0.06
    альному
    -0.06
     uống
    -0.06
    POSITIVE LOGITS
    alink
    0.07
    484
    0.07
    -Class
    0.07
    -pack
    0.06
    (KERN
    0.06
    NET
    0.06
     Net
    0.06
     اتحاد
    0.06
    Vi
    0.06
     nurse
    0.06
    Act Density 0.000%

    No Known Activations