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

    Neuronpedia

    INDEX
    Explanations

    create and define

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anamh
    0.41
    ོང་
    0.40
    órmula
    0.38
     সন্দ
    0.38
     coefficient
    0.37
     coeficiente
    0.37
    aima
    0.37
    编译器
    0.37
    ano
    0.36
    ona
    0.36
    POSITIVE LOGITS
     созда
    0.61
     created
    0.57
    定义
    0.56
    定义的
    0.55
     Define
    0.55
     створе
    0.55
     defined
    0.54
     creada
    0.52
     défini
    0.52
     definiciones
    0.51
    Act Density 0.301%

    No Known Activations