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

    Neuronpedia

    INDEX
    Explanations

    defines fundamental concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ிற்
    0.43
     Amb
    0.41
     Nexus
    0.41
     Kar
    0.39
     Nella
    0.39
     Past
    0.39
    ấn
    0.38
     mess
    0.37
    Kar
    0.37
     Zach
    0.37
    POSITIVE LOGITS
    櫛
    0.45
    栉
    0.42
    ngen
    0.41
     anál
    0.41
    inputArr
    0.41
    OPTV
    0.41
     زیبایی
    0.39
    GetAll
    0.39
    obacterial
    0.39
    痊
    0.38
    Act Density 0.001%

    No Known Activations