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

    Neuronpedia

    INDEX
    Explanations

    decision-making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hosting
    -0.09
    HOST
    -0.09
    Recycler
    -0.08
    PHY
    -0.08
    Friend
    -0.08
    Hosting
    -0.08
    Pack
    -0.08
     Guest
    -0.08
    (host
    -0.08
     guest
    -0.08
    POSITIVE LOGITS
     decision
    0.15
     નિર્ણય
    0.15
     निर्णय
    0.14
     Decision
    0.14
    Decision
    0.14
     Entscheid
    0.14
    决
    0.13
     deliber
    0.13
    decision
    0.13
     تصمیم
    0.12
    Act Density 0.044%

    No Known Activations