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

    Neuronpedia

    INDEX
    Explanations

    treating conditions and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    し
    1.30
    ни
    1.13
     conducción
    1.08
    ో
    0.95
    ä
    0.95
     contaminación
    0.93
     teléfono
    0.92
     înc
    0.92
     inversión
    0.91
     transformación
    0.91
    POSITIVE LOGITS
    n
    1.23
    اد
    1.09
    al
    1.07
    v
    0.93
    ung
    0.92
    f
    0.92
    man
    0.88
     Treating
    0.88
    k
    0.82
    д
    0.82
    Act Density 0.016%

    No Known Activations