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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     på
    -0.06
    -spacing
    -0.06
     lạnh
    -0.06
     hus
    -0.06
     shirts
    -0.06
     lij
    -0.06
     SUPPORT
    -0.06
     Niet
    -0.06
    錢
    -0.06
     خاص
    -0.06
    POSITIVE LOGITS
     WOM
    0.07
    الأ
    0.07
    rum
    0.07
    νοια
    0.06
     Sally
    0.06
     ↵        ↵
    0.06
    veys
    0.06
     цар
    0.06
    roma
    0.06
    ekte
    0.06
    Act Density 0.000%

    No Known Activations