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

    Neuronpedia

    INDEX
    Explanations

    Code or punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     })),↵
    -0.07
     cavalry
    -0.06
     puis
    -0.06
    amet
    -0.06
    灯
    -0.06
     обов
    -0.06
     chấp
    -0.06
    UserId
    -0.06
    .codec
    -0.06
     Zhang
    -0.06
    POSITIVE LOGITS
    ر
    0.06
    scalar
    0.06
    args
    0.06
     decay
    0.06
    .intersection
    0.06
    :false
    0.06
    %%
    0.06
    MHz
    0.06
    .substring
    0.06
    脂
    0.06
    Act Density 0.000%

    No Known Activations