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

    Neuronpedia

    INDEX
    Explanations

    rats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ẳ
    -0.07
     excer
    -0.06
    خص
    -0.06
    <article
    -0.06
     Employer
    -0.06
     Enemy
    -0.06
    ॉर
    -0.06
     angled
    -0.06
    setTitle
    -0.06
     distribute
    -0.06
    POSITIVE LOGITS
     rats
    0.25
     xls
    0.07
     CODE
    0.06
     Кроме
    0.06
    .standard
    0.06
    _EQ
    0.06
     Gat
    0.06
    eds
    0.06
    ейств
    0.06
     kodu
    0.06
    Act Density 0.004%

    No Known Activations