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

    Neuronpedia

    INDEX
    Explanations

    execute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    比較
    -0.06
     będzie
    -0.06
    %%
    -0.06
     stations
    -0.06
     scared
    -0.06
    shade
    -0.06
     DES
    -0.05
    them
    -0.05
     varies
    -0.05
    Perfect
    -0.05
    POSITIVE LOGITS
    .Transform
    0.07
     Прав
    0.07
    background
    0.07
     гру
    0.06
     이전
    0.06
    LAG
    0.06
    revision
    0.06
     reloc
    0.06
     `_
    0.06
    병
    0.06
    Act Density 0.003%

    No Known Activations