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

    Neuronpedia

    INDEX
    Explanations

    lacks specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     två
    0.54
     wody
    0.51
     outflow
    0.50
     input
    0.50
     utilisent
    0.50
     dua
    0.48
     deux
    0.48
     fluctuation
    0.48
     iki
    0.48
     دو
    0.48
    POSITIVE LOGITS
    ౌ
    0.45
    ాల్లో
    0.41
     Kentucky
    0.40
    Tat
    0.39
    ristown
    0.39
    లో
    0.39
    లె
    0.38
    Kentucky
    0.38
    ট
    0.38
    犷
    0.38
    Act Density 0.000%

    No Known Activations