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

    Neuronpedia

    INDEX
    Explanations

    also, too, as well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inline
    0.30
     mA
    0.29
     imageData
    0.29
     args
    0.29
     executable
    0.29
     executing
    0.28
     thay
    0.28
    创建一个
    0.28
     indicate
    0.27
     manually
    0.27
    POSITIVE LOGITS
    yrıca
    0.39
     też
    0.38
     همچنین
    0.37
     также
    0.36
     또한
    0.34
     También
    0.33
    इसलिए
    0.33
     ასევე
    0.32
     Также
    0.32
     आल्सो
    0.31
    Act Density 0.400%

    No Known Activations