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

    Neuronpedia

    INDEX
    Explanations

    =======

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bab
    -0.07
     gluten
    -0.06
     Te
    -0.06
    ivan
    -0.06
    İs
    -0.06
     reporter
    -0.06
    )(_
    -0.06
    "x
    -0.06
     prostitution
    -0.06
     sparks
    -0.06
    POSITIVE LOGITS
    .getMethod
    0.07
    γραφή
    0.07
     уменьш
    0.07
    .Quad
    0.06
    (delete
    0.06
    .relationship
    0.06
     кожного
    0.06
    nums
    0.06
    (it
    0.06
    .ย
    0.06
    Act Density 0.004%

    No Known Activations