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

    Neuronpedia

    INDEX
    Explanations

    Research papers / citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    两
    -0.09
    固
    -0.08
    аць
    -0.08
     habit
    -0.08
    兩
    -0.07
    承担
    -0.07
    两个
    -0.07
    产生
    -0.07
     faltar
    -0.07
     Encycl
    -0.07
    POSITIVE LOGITS
     et
    0.09
    ?,?,?,?,
    0.09
     ...,
    0.09
     മുതൽ
    0.08
    UIApplication
    0.08
     físicas
    0.08
     आदि
    0.08
     ....↵↵
    0.08
    ...,
    0.07
     વગેરે
    0.07
    Act Density 0.012%

    No Known Activations