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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attributed
    -0.07
     Recommendations
    -0.07
    ř
    -0.07
    奏
    -0.07
     lives
    -0.06
    _utilities
    -0.06
     比
    -0.06
     Elements
    -0.06
     ritual
    -0.06
     Corps
    -0.06
    POSITIVE LOGITS
    �
    0.07
     μη
    0.07
     germany
    0.06
     shutil
    0.06
     �
    0.06
        ↵    ↵    ↵
    0.06
     TMPro
    0.06
    _ATOMIC
    0.06
    ây
    0.06
    ">--}}↵
    0.06
    Act Density 0.153%

    No Known Activations