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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia categories and links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /utils
    -0.07
    instruction
    -0.06
    drawable
    -0.06
    suite
    -0.06
    ستر
    -0.06
    award
    -0.06
     binder
    -0.06
    	damage
    -0.06
     nutrit
    -0.06
    uts
    -0.06
    POSITIVE LOGITS
     Moran
    0.06
     yeterli
    0.06
     příjem
    0.06
    _TITLE
    0.06
     yyyy
    0.06
     chiều
    0.06
     asteroids
    0.06
    axy
    0.06
    Cách
    0.06
    ภาพยนตร
    0.06
    Act Density 0.012%

    No Known Activations