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

    Neuronpedia

    INDEX
    Explanations

    rotation and scale transformations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oten
    0.42
    0
    0.41
    agger
    0.38
     redress
    0.37
    aucet
    0.36
     equal
    0.36
     objetivo
    0.36
    HHHH
    0.35
    न्ध
    0.35
     registro
    0.35
    POSITIVE LOGITS
     lương
    0.46
     Blynk
    0.44
    spieler
    0.44
    seite
    0.43
    ༧
    0.43
     Aś
    0.42
    0.42
    ctime
    0.41
     khiến
    0.41
    ルの
    0.41
    Act Density 0.000%

    No Known Activations