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

    Neuronpedia

    INDEX
    Explanations

    HTML attribute assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calcareous
    0.33
     fertilized
    0.28
     mucous
    0.28
    OLYBD
    0.27
     phleg
    0.27
     intramolecular
    0.26
    imethyl
    0.26
     言っ
    0.26
    thisTrack
    0.26
     carnivorous
    0.25
    POSITIVE LOGITS
     API
    0.30
    Config
    0.30
    0
    0.29
    Open
    0.29
    API
    0.27
    s
    0.27
    通过
    0.27
    M
    0.27
    和
    0.27
    客户端
    0.27
    Act Density 2.754%

    No Known Activations