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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    евых
    -0.07
     울
    -0.07
    uyệ
    -0.06
     téc
    -0.06
     понима
    -0.06
     incons
    -0.06
     призна
    -0.06
    verte
    -0.06
     entsprech
    -0.06
    ánd
    -0.06
    POSITIVE LOGITS
     fleeting
    0.07
    .registration
    0.06
     สามารถ
    0.06
     above
    0.06
    156
    0.06
     един
    0.06
     Collision
    0.06
     cigars
    0.06
    �
    0.06
    Entered
    0.06
    Act Density 0.020%

    No Known Activations