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

    Neuronpedia

    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Time
    -0.07
     собствен
    -0.07
    IZE
    -0.07
    pygame
    -0.07
    aleb
    -0.06
    어
    -0.06
     ア
    -0.06
    nesc
    -0.06
    이어
    -0.06
    ア
    -0.06
    POSITIVE LOGITS
     Floral
    0.07
    -place
    0.06
    530
    0.06
     sevent
    0.06
     tonight
    0.06
     Por
    0.06
     ден
    0.06
    valuator
    0.06
    Rotation
    0.06
     pulled
    0.06
    Act Density 0.017%

    No Known Activations