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

    Neuronpedia

    INDEX
    Explanations

    actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    1.19
    一个
    1.18
     adanya
    1.07
    म
    1.04
     autoimmune
    1.02
    不良
    0.98
    なって
    0.98
    />
    0.97
    なった
    0.96
    हित्य
    0.96
    POSITIVE LOGITS
     bipartisan
    1.28
    downs
    1.20
    BOAT
    1.17
     показатель
    1.15
     compter
    1.14
    ाइट
    1.13
    dad
    1.13
    اے
    1.11
    tidak
    1.11
     UserController
    1.11
    Act Density 0.000%

    No Known Activations