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

    Neuronpedia

    INDEX
    Explanations

    simple and easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರಿನ
    0.61
    цыяна
    0.46
     दर्शाता
    0.45
    रासायनिक
    0.43
    噻
    0.43
    ṇa
    0.42
    膻
    0.41
     tejto
    0.40
    প্যাথ
    0.40
    бри
    0.40
    POSITIVE LOGITS
     quas
    0.48
     simples
    0.48
    कायदा
    0.43
    -
    0.42
     간단
    0.42
    0.42
     hull
    0.41
     simple
    0.40
     وما
    0.40
     mainly
    0.40
    Act Density 0.000%

    No Known Activations