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

    Neuronpedia

    INDEX
    Explanations

    pip install python packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prevState
    0.43
    朧
    0.41
    躬
    0.41
     repayment
    0.39
     tempData
    0.39
    チ
    0.39
     groin
    0.39
     Aron
    0.39
    ائل
    0.39
     regiment
    0.39
    POSITIVE LOGITS
    install
    0.99
     install
    0.98
    uptools
    0.95
    py
    0.87
     Py
    0.86
    安装
    0.86
     安装
    0.86
     Install
    0.86
     installs
    0.83
     instalar
    0.82
    Act Density 0.032%

    No Known Activations