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

    Neuronpedia

    INDEX
    Explanations

    foreign words and sucrose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Windows
    0.46
    windows
    0.42
     Windows
    0.42
     complica
    0.41
    バランス
    0.41
    yuan
    0.41
     OUTPUT
    0.41
    ካ
    0.40
    brella
    0.40
    cription
    0.39
    POSITIVE LOGITS
    س
    0.47
     aki
    0.46
     akut
    0.45
     notwendig
    0.44
    劦
    0.43
    સ
    0.43
     blanca
    0.43
     necesarios
    0.42
     bakter
    0.42
    Dyn
    0.42
    Act Density 0.001%

    No Known Activations