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

    Neuronpedia

    INDEX
    Explanations

    negative connotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oned
    0.95
    ма
    0.93
     Правда
    0.91
     successfully
    0.91
    it
    0.91
    ial
    0.90
    αν
    0.89
     ventajas
    0.86
    inde
    0.85
    нина
    0.85
    POSITIVE LOGITS
    ग्रस्त
    1.16
    PhotoMode
    0.85
     Worse
    0.85
     состоянии
    0.84
    グリップ
    0.83
    ע
    0.83
     Dich
    0.82
     akibat
    0.82
    lands
    0.80
     Gebiet
    0.80
    Act Density 1.658%

    No Known Activations