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

    Neuronpedia

    INDEX
    Explanations

    AI agent components and execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ti
    0.50
    ubit
    0.44
    ator
    0.44
    ici
    0.43
     teenage
    0.43
    ornos
    0.42
    statistik
    0.42
    teenage
    0.41
     Peltier
    0.41
    uberculosis
    0.41
    POSITIVE LOGITS
    네
    0.48
    ارين
    0.47
     organizada
    0.46
    ع
    0.46
    座標
    0.44
     avem
    0.44
     rameaux
    0.44
    جين
    0.43
     apud
    0.43
    心得
    0.43
    Act Density 0.000%

    No Known Activations