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

    Neuronpedia

    INDEX
    Explanations

    made of or built from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vanaf
    0.41
    written
    0.37
     MATLAB
    0.36
    produced
    0.35
    Produced
    0.35
    uja
    0.35
     escrita
    0.35
     पढ़कर
    0.35
     نوشته
    0.34
    Developed
    0.34
    POSITIVE LOGITS
     из
    0.75
     out
    0.64
     outta
    0.64
     із
    0.57
     daraus
    0.53
     composed
    0.52
    Из
    0.51
    ből
    0.50
    માંથી
    0.49
    outof
    0.49
    Act Density 0.009%

    No Known Activations