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

    Neuronpedia

    INDEX
    Explanations

    default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ibn
    -0.07
     Stop
    -0.07
     climbs
    -0.06
    -work
    -0.06
    Customer
    -0.06
     Leigh
    -0.06
    -0.06
    .Timestamp
    -0.06
    -0.06
    ='${
    -0.06
    POSITIVE LOGITS
     přece
    0.07
     indem
    0.07
     defaulted
    0.07
    IGHL
    0.07
     playwright
    0.06
    .this
    0.06
     кажд
    0.06
    τύ
    0.06
    케
    0.06
    URAL
    0.06
    Act Density 0.001%

    No Known Activations