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

    Neuronpedia

    INDEX
    Explanations

    numbers and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ską
    0.44
     Interrupt
    0.42
    เดินทาง
    0.41
     Plugins
    0.41
    ակ
    0.41
     Tern
    0.41
     Puedes
    0.41
     Scaffold
    0.40
     peux
    0.39
    创建一个
    0.39
    POSITIVE LOGITS
     offered
    0.53
     presented
    0.46
     ofrec
    0.45
     version
    0.45
     photographed
    0.44
     debuted
    0.44
     debut
    0.43
     submitted
    0.43
     introduced
    0.41
     modeled
    0.40
    Act Density 0.017%

    No Known Activations