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

    Neuronpedia

    INDEX
    Explanations

    model response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Munch
    0.42
     Kong
    0.41
     j
    0.40
     IP
    0.40
     Iraq
    0.39
     Ebola
    0.38
     Irak
    0.38
     दिग्विजय
    0.38
     Mund
    0.37
     Kamp
    0.37
    POSITIVE LOGITS
     балко
    0.46
    કાર
    0.43
    ట్టిన
    0.42
    坐标
    0.40
    CLionProjects
    0.40
    ewski
    0.40
    Netherlands
    0.39
     Couleur
    0.39
     ц
    0.39
    Clothes
    0.39
    Act Density 0.000%

    No Known Activations