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

    Neuronpedia

    INDEX
    Explanations

    irrelevant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    option
    -0.08
    роф
    -0.07
    .shop
    -0.07
     Close
    -0.07
    .complete
    -0.07
     동
    -0.07
     Finish
    -0.07
    Fl
    -0.07
    De
    -0.07
     의
    -0.07
    POSITIVE LOGITS
     سوى
    0.08
    ితం
    0.08
     asupra
    0.08
     Commissie
    0.08
     passieren
    0.08
     except
    0.08
     незалеж
    0.08
     بالنسبة
    0.08
     naha
    0.08
     తెలిసిందే
    0.07
    Act Density 0.009%

    No Known Activations