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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bus
    -0.07
     boiler
    -0.06
     MEMORY
    -0.06
     len
    -0.06
     bul
    -0.06
    .Pow
    -0.06
    _sol
    -0.06
     sys
    -0.06
     Ben
    -0.06
     Ty
    -0.06
    POSITIVE LOGITS
     先
    0.07
     next
    0.07
    似
    0.07
    yect
    0.07
    Future
    0.06
     Future
    0.06
    突然
    0.06
    511
    0.06
    (artist
    0.06
    щий
    0.06
    Act Density 0.008%

    No Known Activations