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

    Neuronpedia

    INDEX
    Explanations

    built by or designed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fornece
    0.42
    یدہ
    0.40
     כי
    0.39
    暝
    0.39
    طفال
    0.39
     disertai
    0.39
     كما
    0.38
    침
    0.38
    即可
    0.38
    وره
    0.37
    POSITIVE LOGITS
     t
    0.42
     Kiy
    0.40
     Activision
    0.40
     Jesse
    0.39
     an
    0.39
     Academy
    0.38
     Steve
    0.38
     accounting
    0.38
    iras
    0.38
     investigated
    0.37
    Act Density 0.000%

    No Known Activations