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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asynchronous
    -0.09
    聞く
    -0.07
    おく
    -0.07
    -
    -0.07
    ㈔
    -0.07
     Persistent
    -0.07
    --+
    -0.07
    第十
    -0.07
    ern
    -0.07
     As
    -0.07
    POSITIVE LOGITS
    源
    0.08
    家纺
    0.07
    UFF
    0.07
    >Loading
    0.07
    مان
    0.07
    一族
    0.07
     WAN
    0.07
    닷
    0.07
    UNC
    0.07
     Tử
    0.07
    Act Density 0.065%

    No Known Activations