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

    Neuronpedia

    INDEX
    Explanations

    code snippets and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ést
    -0.07
    =z
    -0.06
    ナル
    -0.06
    .Quantity
    -0.06
     after
    -0.06
     moi
    -0.06
     stress
    -0.06
    -normal
    -0.06
     elephant
    -0.06
    .She
    -0.06
    POSITIVE LOGITS
     北京
    0.07
     инструмент
    0.07
     τον
    0.07
    lcd
    0.06
    Hallo
    0.06
     pojištění
    0.06
     dictionaryWith
    0.06
    複
    0.06
     Mitchell
    0.06
     Helpful
    0.06
    Act Density 0.000%

    No Known Activations