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

    Neuronpedia

    INDEX
    Explanations

    timestamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /O
    -0.06
    оке
    -0.06
     underwater
    -0.06
    .Move
    -0.06
     startling
    -0.06
     시
    -0.06
     rectangular
    -0.06
    -legged
    -0.06
     microseconds
    -0.06
     fragmentation
    -0.06
    POSITIVE LOGITS
    альные
    0.07
     Суд
    0.07
    >*/↵
    0.07
    ++)↵
    0.06
     Оп
    0.06
    Best
    0.06
     undermines
    0.06
     gallery
    0.06
    剑
    0.06
     Για
    0.06
    Act Density 0.010%

    No Known Activations