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

    Neuronpedia

    INDEX
    Explanations

    reasonable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    れど
    -0.07
    leitung
    -0.06
     bullshit
    -0.06
    зація
    -0.06
    fileName
    -0.06
    -equ
    -0.06
    겨
    -0.06
    %p
    -0.06
    _MUT
    -0.06
     borough
    -0.06
    POSITIVE LOGITS
    (Employee
    0.07
     qx
    0.07
     comrades
    0.07
    choices
    0.07
    (norm
    0.06
     partnership
    0.06
    farm
    0.06
    (Pos
    0.06
    twig
    0.06
    _ITEM
    0.06
    Act Density 0.002%

    No Known Activations