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

    Neuronpedia

    INDEX
    Explanations

    keywords followed by "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ologici
    0.87
    чни
    0.86
    वणे
    0.85
    хі
    0.85
     Blonde
    0.85
    acije
    0.84
     முடியாது
    0.83
    attan
    0.82
     بالس
    0.81
    പാടി
    0.81
    POSITIVE LOGITS
      
    0.81
     one
    0.62
     consult
    0.61
     (
    0.60
    l
    0.60
    one
    0.59
     which
    0.59
     that
    0.57
     also
    0.57
    formerly
    0.56
    Act Density 0.338%

    No Known Activations