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

    Neuronpedia

    INDEX
    Explanations

    give a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solely
    0.60
     agonist
    0.58
     desenvol
    0.55
     only
    0.54
    ই
    0.54
     सिर्फ
    0.52
     el
    0.51
     config
    0.51
     và
    0.51
    よりも
    0.50
    POSITIVE LOGITS
     некоторое
    0.64
    t
    0.58
     некоторые
    0.57
    other
    0.57
    ються
    0.57
     другими
    0.57
    autres
    0.56
    é
    0.56
    .}
    0.55
    h
    0.55
    Act Density 0.575%

    No Known Activations