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

    Neuronpedia

    INDEX
    Explanations

    control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     melhorar
    0.36
     সত
    0.36
     सीएचएसएल
    0.36
     wst
    0.36
     Pell
    0.35
     deficiencies
    0.35
     להי
    0.35
     erreur
    0.35
     bienvenidas
    0.35
    悟
    0.35
    POSITIVE LOGITS
     control
    2.56
    control
    2.33
    控制
    2.30
    Control
    2.22
     kontrol
    2.17
     контроля
    2.17
     контроль
    2.17
     Kontrolle
    2.17
     Control
    2.14
     controllo
    2.14
    Act Density 0.081%

    No Known Activations