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

    Neuronpedia

    INDEX
    Explanations

    ASGI server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     通常
    0.44
     conventionally
    0.42
     byg
    0.41
    onymous
    0.40
    েরই
    0.40
     白色
    0.40
     lifetimes
    0.39
     Wikipedia
    0.39
     either
    0.39
     cycles
    0.38
    POSITIVE LOGITS
     storie
    0.58
     falsa
    0.50
    मिक
    0.46
     Chimie
    0.46
     storia
    0.45
    ancipation
    0.44
     ciencia
    0.44
    ᱔
    0.43
    ﺠ
    0.43
    Story
    0.42
    Act Density 0.001%

    No Known Activations