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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kilograms
    -0.07
    akhir
    -0.06
     Kom
    -0.06
     toler
    -0.06
    rhs
    -0.06
    Cars
    -0.06
    urances
    -0.06
     kapsam
    -0.06
     Neue
    -0.06
     wichtig
    -0.06
    POSITIVE LOGITS
     Children
    0.08
    .fillStyle
    0.06
    'é
    0.06
    hread
    0.06
    -video
    0.06
    .box
    0.06
    ूर
    0.06
     moistur
    0.06
    映
    0.06
    ResourceManager
    0.06
    Act Density 0.041%

    No Known Activations