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

    Neuronpedia

    INDEX
    Explanations

    business rankings & news sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .,"
    0.43
    ज़ा
    0.40
    ?"
    0.39
    侔
    0.39
    ,"
    0.38
    xiang
    0.38
     bụ
    0.37
     Nij
    0.37
     integrante
    0.37
     કરી
    0.37
    POSITIVE LOGITS
    SW
    0.41
     juniper
    0.40
     liquids
    0.38
    POST
    0.37
    mias
    0.37
     lordship
    0.37
     cartridges
    0.36
     outpost
    0.36
     incarcer
    0.36
    각형
    0.36
    Act Density 0.014%

    No Known Activations