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

    Neuronpedia

    INDEX
    Explanations

    Bootstrap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lan
    0.45
    othe
    0.40
    Facebook
    0.39
    rou
    0.38
    ,=
    0.38
    l
    0.38
    ý
    0.38
    ransition
    0.37
    land
    0.36
    sl
    0.36
    POSITIVE LOGITS
     Journey
    0.43
    টিশ
    0.42
     Producers
    0.42
     내용
    0.42
     Saw
    0.41
    nX
    0.41
     Accelerator
    0.41
     Predator
    0.40
    ToInt
    0.40
     GRID
    0.40
    Act Density 0.001%

    No Known Activations