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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mornings
    -0.06
     Tile
    -0.06
     CY
    -0.06
     tabs
    -0.06
     msg
    -0.06
     altar
    -0.06
     guideline
    -0.06
    -0.06
    ='+
    -0.05
     hierarchy
    -0.05
    POSITIVE LOGITS
     edilmesi
    0.07
    ใด
    0.07
    (^
    0.07
    ((_
    0.07
    abytes
    0.06
     инструмент
    0.06
    _pet
    0.06
     artikel
    0.06
    curring
    0.06
    otence
    0.06
    Act Density 0.021%

    No Known Activations