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

    Neuronpedia

    INDEX
    Explanations

    business, learning, Surface, src

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oldCount
    0.38
    崛
    0.38
     snakes
    0.37
     trailbl
    0.36
    飆
    0.36
     stash
    0.35
     convain
    0.35
    വില്‍
    0.35
    萬
    0.34
     vendido
    0.34
    POSITIVE LOGITS
     Poor
    0.43
     Eller
    0.36
     Gareth
    0.36
    Poor
    0.36
    aq
    0.35
     Priest
    0.35
     Hark
    0.35
     ź
    0.35
     Freed
    0.35
    冯
    0.35
    Act Density 0.000%

    No Known Activations