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

    Neuronpedia

    INDEX
    Explanations

    teaching and learning from data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರ್ಶ
    0.51
    ва
    0.49
    <0xA5>
    0.47
    旅遊
    0.46
    뇰
    0.46
     síntomas
    0.46
    音乐
    0.45
     пыта
    0.45
    唵
    0.44
     обеща
    0.44
    POSITIVE LOGITS
     SLAs
    0.52
     Prerequisites
    0.52
     prisms
    0.50
     contaminants
    0.50
     Wakefield
    0.50
     Cables
    0.46
     Testing
    0.46
     Adults
    0.46
     connectors
    0.45
     Serving
    0.44
    Act Density 0.003%

    No Known Activations