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

    Neuronpedia

    INDEX
    Explanations

    open a terminal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ু
    0.68
    ین
    0.61
     áo
    0.58
    ل
    0.57
    ir
    0.56
    си
    0.56
    سي
    0.56
     пенсии
    0.55
    ט
    0.55
    写法
    0.54
    POSITIVE LOGITS
     Opens
    0.96
     Opening
    0.90
     ouvert
    0.90
     opens
    0.88
     Opened
    0.84
     abiertos
    0.82
     åp
    0.81
     opened
    0.80
     öpp
    0.79
    Opened
    0.78
    Act Density 0.041%

    No Known Activations