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

    Neuronpedia

    INDEX
    Explanations

    providing services or goods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    X
    0.61
    Z
    0.55
    Γ
    0.55
    𝐝
    0.55
     mache
    0.54
    ت
    0.54
    כון
    0.53
    ADE
    0.52
    י
    0.52
     galle
    0.51
    POSITIVE LOGITS
    </h3>
    0.63
    ーター
    0.56
    ğu
    0.55
     imparting
    0.55
     Jalan
    0.54
     Caring
    0.54
     ஆனால்
    0.52
    મને
    0.52
     Thương
    0.50
    ীন
    0.50
    Act Density 0.020%

    No Known Activations