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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     často
    -0.06
     тка
    -0.06
     Locator
    -0.06
    '↵↵↵
    -0.06
     handleClick
    -0.05
     вну
    -0.05
     Б
    -0.05
     jewels
    -0.05
     Από
    -0.05
     jp
    -0.05
    POSITIVE LOGITS
     inoc
    0.07
     HIT
    0.07
    貴
    0.07
    essa
    0.07
    ラン
    0.06
     dị
    0.06
    \Entity
    0.06
    _TRIANGLE
    0.06
    ^-
    0.06
     differ
    0.06
    Act Density 0.091%

    No Known Activations