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

    Neuronpedia

    INDEX
    Explanations

    method calls and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мут
    0.98
    bearer
    0.93
    вам
    0.89
    Serialized
    0.88
     CORPER
    0.86
    ྥ
    0.85
    COMMIT
    0.84
    squiggle
    0.84
    BMP
    0.84
    твы
    0.84
    POSITIVE LOGITS
    sey
    0.87
     Colonel
    0.84
     suc
    0.82
    oy
    0.82
    usters
    0.80
    ane
    0.79
    ron
    0.79
     caranya
    0.79
    ire
    0.79
    uls
    0.78
    Act Density 0.002%

    No Known Activations