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

    Neuronpedia

    INDEX
    Explanations

    parent-child

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     birbir
    -0.08
     ль
    -0.07
    络
    -0.07
    ESİ
    -0.06
    assword
    -0.06
     亚洲
    -0.06
    _soup
    -0.06
     Lakers
    -0.06
    烈
    -0.06
     Ply
    -0.06
    POSITIVE LOGITS
     against
    0.07
     very
    0.07
     verification
    0.07
    (dirname
    0.06
    _EVENT
    0.06
     disput
    0.06
     xương
    0.06
     THIS
    0.06
     condol
    0.06
    (choice
    0.06
    Act Density 0.038%

    No Known Activations