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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    íme
    -0.07
    -wheel
    -0.07
    _intersection
    -0.06
    ﾆ
    -0.06
    _const
    -0.06
    ejte
    -0.06
     colorWithRed
    -0.06
    /rand
    -0.06
    ={`/
    -0.06
    été
    -0.06
    POSITIVE LOGITS
     Evaluation
    0.07
    영
    0.06
     ráp
    0.06
    0.06
    Fu
    0.06
     vagina
    0.06
     coffee
    0.06
     Entered
    0.06
    BUILD
    0.06
     cfg
    0.06
    Act Density 0.029%

    No Known Activations