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

    Neuronpedia

    INDEX
    Explanations

    following up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tells
    0.42
    沉默
    0.42
     lately
    0.42
     объяс
    0.42
     skyl
    0.42
    Ferr
    0.41
    沟通
    0.41
     comunica
    0.41
    告诉
    0.41
     telling
    0.41
    POSITIVE LOGITS
     bump
    2.25
     Bump
    2.14
    bump
    2.11
    Bump
    2.11
     bumps
    2.06
     bumping
    2.03
     bumped
    1.95
    bumps
    1.73
     bumpers
    1.07
     bumpy
    0.91
    Act Density 0.006%

    No Known Activations