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

    Neuronpedia

    INDEX
    Explanations

    1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alak
    0.36
    lecting
    0.36
    ដែលមាន
    0.35
    packages
    0.35
     ஆசிரிய
    0.34
     uống
    0.34
     ని
    0.34
    তের
    0.34
     давайте
    0.34
    arak
    0.33
    POSITIVE LOGITS
     custody
    0.37
     lewis
    0.36
     muster
    0.36
     obje
    0.34
     LayoutInflater
    0.33
     smer
    0.33
     型
    0.33
    คัญ
    0.32
    ტურ
    0.32
     newbie
    0.32
    Act Density 0.032%

    No Known Activations