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

    Neuronpedia

    INDEX
    Explanations

    Average of numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \&
    0.43
    勻
    0.40
     voulais
    0.39
    समाज
    0.37
     kamu
    0.37
     Découvrez
    0.36
     대한민국
    0.36
     Allie
    0.36
    美國
    0.36
    selectable
    0.36
    POSITIVE LOGITS
     Abhäng
    0.39
     circ
    0.38
     swo
    0.38
    ".*:
    0.37
    दाता
    0.36
    litre
    0.35
    他に
    0.35
     lumber
    0.35
    landscape
    0.34
     crashing
    0.34
    Act Density 0.000%

    No Known Activations