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

    Neuronpedia

    INDEX
    Explanations

    product versions or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     industry
    0.64
     kurum
    0.62
     companies
    0.61
     пунк
    0.60
     organization
    0.58
    公司的
    0.57
     company
    0.57
    供给
    0.56
     organización
    0.55
     falando
    0.55
    POSITIVE LOGITS
    Ⅱ
    1.11
    PLUS
    1.09
     Lite
    1.06
     Plus
    1.03
    Plus
    1.00
    VII
    1.00
    plus
    0.99
     플러스
    0.99
     FINAL
    0.98
    Ⅴ
    0.98
    Act Density 0.705%

    No Known Activations