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

    Neuronpedia

    INDEX
    Explanations

    scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odies
    0.43
     muertos
    0.40
     Brav
    0.40
    ديث
    0.37
     antaranya
    0.36
     fired
    0.36
     기본적인
    0.36
     款
    0.35
     cannons
    0.35
    దిక
    0.35
    POSITIVE LOGITS
    侗
    0.42
    旧
    0.39
     руко
    0.38
     সুবিধা
    0.38
    Gray
    0.38
    蔺
    0.37
     Нов
    0.36
    erp
    0.36
    collar
    0.36
    绢
    0.36
    Act Density 0.007%

    No Known Activations