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

    Neuronpedia

    INDEX
    Explanations

    choice or selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உண்டு
    0.43
    physik
    0.42
    含义
    0.41
    UnaryOperation
    0.40
     ಇನ್ನ
    0.40
    iculos
    0.40
    csim
    0.39
    ANU
    0.39
    ürdig
    0.39
    טל
    0.38
    POSITIVE LOGITS
     chose
    1.08
    选择
    1.07
     choisi
    1.06
     prefer
    1.05
    選擇
    1.03
     tercih
    1.03
     escolh
    1.02
     выборе
    1.02
     선택
    1.02
     предпоч
    1.02
    Act Density 0.240%

    No Known Activations