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

    Neuronpedia

    INDEX
    Explanations

    family, children, and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    絖
    0.27
     выска
    0.26
     ū
    0.25
     они
    0.24
     ஏற்க
    0.24
    PLOY
    0.24
     दिवा
    0.23
    ั
    0.23
     pect
    0.23
    0.23
    POSITIVE LOGITS
     before
    0.27
     three
    0.27
     ግራም
    0.27
     builder
    0.26
    នៃ
    0.26
     narrow
    0.26
     melts
    0.26
     perpendicular
    0.25
    rende
    0.25
     formidable
    0.25
    Act Density 0.000%

    No Known Activations