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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +-+-+-+-
    -0.06
     바로
    -0.06
    tensor
    -0.06
     jednot
    -0.06
     frat
    -0.06
    界
    -0.06
    ики
    -0.06
    .Network
    -0.06
    (inertia
    -0.06
     Tanrı
    -0.06
    POSITIVE LOGITS
    <Employee
    0.07
     jour
    0.06
     arrays
    0.06
     sapi
    0.06
    (parts
    0.06
     overturn
    0.06
     touched
    0.06
    �
    0.06
     flew
    0.06
    Provider
    0.06
    Act Density 0.027%

    No Known Activations