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

    Neuronpedia

    INDEX
    Explanations

    fortifications and historical sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.30
    v
    1.29
    y
    1.26
    g
    1.24
    al
    1.19
    art
    1.16
    o
    1.16
    h
    1.15
    x
    1.14
    in
    1.12
    POSITIVE LOGITS
    न
    1.04
    ه
    0.95
    ন
    0.93
     opér
    0.81
     спосо
    0.81
     âgé
    0.81
     sostanz
    0.81
     eficacia
    0.81
    ма
    0.80
     возраста
    0.80
    Act Density 0.000%

    No Known Activations