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

    Neuronpedia

    INDEX
    Explanations

    feel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noble
    -0.07
     seznam
    -0.07
    612
    -0.07
     Tory
    -0.07
     زنده
    -0.07
    iability
    -0.07
     Transformers
    -0.06
    _answer
    -0.06
     кг
    -0.06
    .listBox
    -0.06
    POSITIVE LOGITS
     thought
    0.06
     Feeling
    0.06
    効
    0.06
    /control
    0.06
     '/')↵
    0.06
     фин
    0.06
    _ut
    0.06
     Nel
    0.06
     direkt
    0.06
     �
    0.06
    Act Density 0.029%

    No Known Activations