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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    细菌
    0.28
     intervención
    0.27
    निमल
    0.25
     ক্যান্সার
    0.25
     Prinzip
    0.25
    丵
    0.25
     públicas
    0.25
    肿瘤
    0.25
     Juden
    0.25
    細菌
    0.24
    POSITIVE LOGITS
    0.29
    .
    0.29
    -
    0.26
     approximately
    0.26
    i
    0.25
    d
    0.25
    ।
    0.25
    +.
    0.25
     .
    0.23
    f
    0.23
    Act Density 0.360%

    No Known Activations