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

    Neuronpedia

    INDEX
    Explanations

    list items or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ib
    0.54
    io
    0.52
    iod
    0.48
    ion
    0.46
    ih
    0.46
    form
    0.46
    finish
    0.46
    ashed
    0.46
    os
    0.44
    ated
    0.44
    POSITIVE LOGITS
     legislação
    0.50
     totalling
    0.42
    Etiam
    0.42
     గత
    0.42
     poesia
    0.41
     Lawyers
    0.40
    硙
    0.40
    Comments
    0.40
     TOTAL
    0.40
     gäller
    0.40
    Act Density 0.141%

    No Known Activations