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

    Neuronpedia

    INDEX
    Explanations

    describing function or ease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     materiality
    0.89
     olduğuna
    0.86
     ஜனநாயக
    0.84
    embangunan
    0.82
     objRequest
    0.82
     linguagem
    0.81
    UTF
    0.80
    規模
    0.80
     Politique
    0.79
     অবকাঠ
    0.79
    POSITIVE LOGITS
     편리
    1.18
     snacking
    1.15
     snacks
    1.09
     wearer
    1.09
     effortlessly
    1.05
     selfies
    1.04
     beverages
    1.02
     protect
    1.01
     feedings
    1.00
     during
    0.98
    Act Density 0.471%

    No Known Activations