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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τες
    -0.08
     Putting
    -0.07
     thoại
    -0.07
    hta
    -0.07
     intel
    -0.07
     hearty
    -0.07
    their
    -0.07
    trash
    -0.07
     бізнес
    -0.06
     Mouth
    -0.06
    POSITIVE LOGITS
     SAVE
    0.07
    834
    0.06
    andering
    0.05
     mitochondrial
    0.05
    ΑΚ
    0.05
    aim
    0.05
    аст
    0.05
    _remaining
    0.05
    ある
    0.05
    άκ
    0.05
    Act Density 0.057%

    No Known Activations