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

    Neuronpedia

    INDEX
    Explanations

    algorithms and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಗದ
    0.41
     paced
    0.39
    California
    0.37
    ymen
    0.37
     tempo
    0.36
    aque
    0.36
     marka
    0.36
    Intersection
    0.35
    ုပ်
    0.35
    SG
    0.35
    POSITIVE LOGITS
     Maureen
    0.43
    leun
    0.41
    dea
    0.39
     асо
    0.39
     mei
    0.39
    elde
    0.39
     jahr
    0.39
     Puritan
    0.39
     carr
    0.38
    mirea
    0.38
    Act Density 0.000%

    No Known Activations