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

    Neuronpedia

    INDEX
    Explanations

    use metal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    обо
    0.43
    Fra
    0.42
     lengths
    0.41
    操
    0.40
     Dirac
    0.38
     leftover
    0.38
    Identify
    0.38
    опера
    0.38
     Identify
    0.37
    Problems
    0.37
    POSITIVE LOGITS
    daq
    0.38
     किस्मत
    0.38
    ซิตี
    0.38
    angk
    0.37
    ('/:
    0.37
    ้วน
    0.37
    ocket
    0.37
    ㄱ
    0.36
    ETIME
    0.36
     ദിവസം
    0.36
    Act Density 0.000%

    No Known Activations