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

    Neuronpedia

    INDEX
    Explanations

    va

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yönet
    0.67
     Fitness
    0.67
     FNA
    0.61
     Fermi
    0.59
    Fitness
    0.59
     Biology
    0.58
     Фер
    0.58
    塬
    0.58
     Biol
    0.58
     Manage
    0.58
    POSITIVE LOGITS
     aisles
    0.58
    ud
    0.57
    que
    0.54
    estre
    0.53
     sketches
    0.53
    UDE
    0.53
     drinkers
    0.52
    culares
    0.52
    cab
    0.52
    iski
    0.51
    Act Density 0.001%

    No Known Activations