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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мис
    -0.06
     दल
    -0.06
     meiner
    -0.06
     hồi
    -0.06
     Cumhurbaş
    -0.06
    ?t
    -0.06
    furt
    -0.06
     rfl
    -0.06
     Todd
    -0.06
     pět
    -0.06
    POSITIVE LOGITS
    .enqueue
    0.08
    alleng
    0.07
    근
    0.07
    vertise
    0.07
    gas
    0.07
    под
    0.07
    -energy
    0.06
    round
    0.06
    very
    0.06
    สามารถ
    0.06
    Act Density 0.056%

    No Known Activations