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

    Neuronpedia

    INDEX
    Explanations

    jobs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     klim
    -0.07
     ва
    -0.07
     exercise
    -0.07
    indexes
    -0.07
    -beta
    -0.07
    IDI
    -0.06
     Олександ
    -0.06
     spos
    -0.06
     giants
    -0.06
     svn
    -0.06
    POSITIVE LOGITS
    Faces
    0.06
    HL
    0.06
     där
    0.06
     Johnston
    0.06
    assignments
    0.06
    。当
    0.06
    ution
    0.06
    _found
    0.06
     ^{}
    0.06
    年的
    0.06
    Act Density 0.071%

    No Known Activations