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

    Neuronpedia

    INDEX
    Explanations

    anthropologist parents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    defineProperty
    0.43
    侮
    0.43
     gentleman
    0.42
     parseFloat
    0.42
    源代码
    0.39
    信する
    0.37
     午前
    0.37
     Prop
    0.37
    ISPW
    0.37
    暴露
    0.37
    POSITIVE LOGITS
    DIM
    0.44
     dw
    0.40
     quitting
    0.39
     incom
    0.39
    Beyond
    0.38
    aryng
    0.38
    RUB
    0.38
    queen
    0.37
    trim
    0.37
     dwelt
    0.37
    Act Density 0.006%

    No Known Activations