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

    Neuronpedia

    INDEX
    Explanations

    visual storytelling and experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পরের
    0.38
    Kyle
    0.37
    反而
    0.37
    d
    0.37
     সম্মেলনে
    0.37
    VU
    0.37
     Slam
    0.36
     Torque
    0.36
     symbolTable
    0.36
    人类
    0.36
    POSITIVE LOGITS
     luke
    0.44
    チル
    0.42
    柰
    0.40
    \...
    0.39
    逕
    0.39
     visa
    0.39
     veneers
    0.39
     establishments
    0.38
    荷重
    0.38
     Nain
    0.37
    Act Density 0.000%

    No Known Activations