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

    Neuronpedia

    INDEX
    Explanations

    sediment, fluid, shoes, contamination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eng
    0.43
     Suzuki
    0.42
     perverse
    0.42
    inn
    0.42
    ally
    0.41
    wing
    0.40
    me
    0.40
     Wann
    0.39
    in
    0.39
    man
    0.39
    POSITIVE LOGITS
     htmlFor
    0.45
    \}$.
    0.44
     asserting
    0.43
    亿美元
    0.43
     COMPLEXES
    0.43
     মসজিদের
    0.43
    新的
    0.42
    新たな
    0.42
    newPage
    0.42
    🏦
    0.42
    Act Density 0.000%

    No Known Activations