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

    Neuronpedia

    INDEX
    Explanations

    spatial and sequential positioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लिए
    0.50
    ovanie
    0.48
    שו
    0.46
    𒀊
    0.46
     लीटर
    0.46
    តម្លៃ
    0.46
    antlr
    0.46
    沇
    0.45
    upné
    0.45
     المثلثيه
    0.45
    POSITIVE LOGITS
     S
    0.48
     M
    0.42
    ↵↵
    0.41
     L
    0.40
     followed
    0.40
     In
    0.40
     Int
    0.39
     The
    0.38
     drag
    0.37
     O
    0.37
    Act Density 0.000%

    No Known Activations