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

    Neuronpedia

    INDEX
    Explanations

    moving or payment directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ফলাফল
    0.39
     параметр
    0.38
    fireFlower
    0.38
    amssymb
    0.37
     Elektrokh
    0.37
    きの
    0.36
     કંઈ
    0.36
    翛
    0.36
    愿意
    0.35
     سيكون
    0.35
    POSITIVE LOGITS
    lines
    0.37
    away
    0.37
     for
    0.35
     to
    0.34
     and
    0.34
    top
    0.34
     bod
    0.34
    r
    0.33
     is
    0.33
    ies
    0.33
    Act Density 0.000%

    No Known Activations