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

    Neuronpedia

    INDEX
    Explanations

    money amounts and data analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    çin
    0.46
    been
    0.44
    Erin
    0.44
    og
    0.43
    Yoga
    0.43
     दिसत
    0.43
     fonbet
    0.43
    ။
    0.43
     φ
    0.42
     قائم
    0.42
    POSITIVE LOGITS
    solver
    0.46
    ಸ
    0.46
    予
    0.46
    る
    0.44
    パス
    0.44
    reacted
    0.44
    msqrt
    0.43
     blamed
    0.42
    nj
    0.42
     przeb
    0.42
    Act Density 0.001%

    No Known Activations