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

    Neuronpedia

    INDEX
    Explanations

    mechanisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stereo
    -0.07
    descending
    -0.06
    capt
    -0.06
     operands
    -0.06
     Kurt
    -0.06
     Nug
    -0.05
     territor
    -0.05
    kB
    -0.05
    ylim
    -0.05
     اختی
    -0.05
    POSITIVE LOGITS
     ging
    0.08
     بالرياض
    0.07
    ritical
    0.07
    .isChecked
    0.07
     literals
    0.06
    /ts
    0.06
     Aires
    0.06
     Structures
    0.06
     sincerely
    0.06
    _PRICE
    0.06
    Act Density 0.008%

    No Known Activations