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

    Neuronpedia

    INDEX
    Explanations

    brains wired to react

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Honey
    0.40
    tot
    0.40
     honey
    0.39
     Honey
    0.38
     prodig
    0.38
     মধু
    0.38
    timelist
    0.37
    开设
    0.37
    بیه
    0.37
     helplessness
    0.36
    POSITIVE LOGITS
    سازی
    0.39
    uyen
    0.39
     снима
    0.37
     sty
    0.37
     টিক
    0.37
     Shuttle
    0.37
    SpriteCollision
    0.36
     下载
    0.36
     downloads
    0.36
     분류
    0.36
    Act Density 0.000%

    No Known Activations