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

    Neuronpedia

    INDEX
    Explanations

    make clean build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ဟုတ်
    0.41
     ჩატი
    0.39
     Gerry
    0.38
    步骤
    0.38
    Add
    0.37
     ब्राह
    0.37
    জন্য
    0.36
    )\|_{\
    0.36
    Addition
    0.36
     управлять
    0.36
    POSITIVE LOGITS
     clean
    0.70
    clean
    0.58
     validate
    0.43
     bersih
    0.43
     limpiar
    0.42
     Clean
    0.42
    Clean
    0.42
     sạch
    0.40
     cleans
    0.40
     limpia
    0.39
    Act Density 0.003%

    No Known Activations