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

    Neuronpedia

    INDEX
    Explanations

    print and show output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    图中
    0.40
    这句话
    0.39
     Progn
    0.38
    inject
    0.38
     fix
    0.38
    يتر
    0.38
    Fix
    0.37
    发射
    0.37
    BinaryOperation
    0.36
    setRoi
    0.36
    POSITIVE LOGITS
     scroll
    0.46
     cukup
    0.42
     काही
    0.42
    概要
    0.42
     aşağı
    0.42
     quelques
    0.42
     daunting
    0.42
     shortlisted
    0.42
    }:\
    0.41
    Showing
    0.41
    Act Density 0.155%

    No Known Activations