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

    Neuronpedia

    INDEX
    Explanations

    Desserts and toppings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دراسة
    -0.09
     إش
    -0.08
     الدراسة
    -0.08
     rigor
    -0.08
     meis
    -0.08
     kupanga
    -0.08
     ګ
    -0.08
     أعضاء
    -0.08
     ಚುನ
    -0.08
     أك
    -0.08
    POSITIVE LOGITS
     sauces
    0.08
     sauce
    0.08
     tablespoon
    0.08
     efter
    0.08
    Dense
    0.07
     rollout
    0.07
    :',
    0.07
     dragging
    0.07
    Eval
    0.07
    :**
    0.07
    Act Density 0.018%

    No Known Activations