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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    James
    -0.07
    ember
    -0.07
    бора
    -0.06
    January
    -0.06
    model
    -0.06
    ateau
    -0.06
     werde
    -0.06
     east
    -0.06
     streak
    -0.06
    _needed
    -0.06
    POSITIVE LOGITS
    。而
    0.06
    nm
    0.06
    .Listen
    0.06
    60
    0.06
     groupId
    0.06
    (Self
    0.06
     chống
    0.06
    。これ
    0.06
    ieme
    0.06
     Οι
    0.06
    Act Density 0.006%

    No Known Activations