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

    Neuronpedia

    INDEX
    Explanations

    revenue distribution and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இருந்து
    0.41
    صیٰ
    0.38
    绰
    0.38
     Nxc
    0.38
    ಗಳಿಂದ
    0.37
     başladı
    0.37
    綽
    0.36
    Bal
    0.36
    عى
    0.35
     区
    0.34
    POSITIVE LOGITS
     goes
    1.15
     Goes
    0.95
    goes
    0.95
     went
    0.91
     går
    0.84
    去的
    0.83
    went
    0.82
    去了
    0.82
     belongs
    0.82
     goto
    0.82
    Act Density 0.019%

    No Known Activations