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

    Neuronpedia

    INDEX
    Explanations

    ites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ~~~~~~~~
    -0.07
     ^
    -0.07
    .*
    -0.07
    .mockito
    -0.07
    言わ
    -0.06
     specialized
    -0.06
    �
    -0.06
    -bootstrap
    -0.06
     愛
    -0.06
    Fu
    -0.06
    POSITIVE LOGITS
    .Async
    0.07
     풀
    0.06
    μεν
    0.06
    コード
    0.06
    .Logging
    0.06
    poly
    0.06
    シ
    0.06
    .EXP
    0.06
    Western
    0.06
    UNC
    0.06
    Act Density 0.000%

    No Known Activations