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

    Neuronpedia

    INDEX
    Explanations

    aiming for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hence
    0.53
     MUST
    0.50
     ইহা
    0.49
     Amongst
    0.49
     Hence
    0.48
     amongst
    0.44
     esempi
    0.44
     ALWAYS
    0.44
    hence
    0.44
    必须要
    0.44
    POSITIVE LOGITS
     כדי
    0.47
     experts
    0.45
     expects
    0.44
     oček
    0.44
     अपेक्षाकृत
    0.42
    Experts
    0.42
    한편
    0.42
    Expect
    0.42
     expect
    0.41
     aim
    0.41
    Act Density 0.023%

    No Known Activations