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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     препара
    -0.07
    ふ
    -0.07
     Thanksgiving
    -0.07
     conscious
    -0.07
     admitted
    -0.07
    amine
    -0.06
    stk
    -0.06
    athroom
    -0.06
     жизнь
    -0.06
    舞
    -0.06
    POSITIVE LOGITS
    Archive
    0.06
    Restr
    0.06
     quyền
    0.06
    ẫ
    0.06
     BorderSide
    0.06
     dẫn
    0.06
     Haziran
    0.05
    ().__
    0.05
    (BASE
    0.05
     radiant
    0.05
    Act Density 0.035%

    No Known Activations