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

    Neuronpedia

    INDEX
    Explanations

    Hotels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stretch
    -0.07
     füh
    -0.07
    lated
    -0.07
    "L
    -0.06
    trusted
    -0.06
    bam
    -0.06
     periodically
    -0.06
     warranted
    -0.06
    Started
    -0.06
     belong
    -0.06
    POSITIVE LOGITS
     Sach
    0.06
     Listings
    0.06
    .newLine
    0.06
    �
    0.06
    _dm
    0.06
     Calc
    0.06
     PartialView
    0.06
     neighbour
    0.06
    ========↵
    0.06
    /Game
    0.06
    Act Density 0.013%

    No Known Activations