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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geomet
    -0.06
     Cleans
    -0.06
     lub
    -0.06
     проте
    -0.06
     projector
    -0.06
     Zhu
    -0.06
     filtration
    -0.06
     cotton
    -0.06
    -0.06
    -0.05
    POSITIVE LOGITS
     vine
    0.07
    -Se
    0.07
    �
    0.07
    说道
    0.06
     salario
    0.06
    azı
    0.06
    보다
    0.06
    iferay
    0.06
     처리
    0.06
     داشتن
    0.06
    Act Density 0.001%

    No Known Activations