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

    Neuronpedia

    INDEX
    Explanations

    gene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    复兴
    -0.08
     thereafter
    -0.07
     assistance
    -0.07
     enormous
    -0.07
     ongoing
    -0.07
    שואה
    -0.07
     plenty
    -0.07
     고
    -0.07
    拊
    -0.07
    סכום
    -0.07
    POSITIVE LOGITS
    ờ
    0.07
    aje
    0.07
    apesh
    0.07
    യ
    0.07
     Jets
    0.07
    _SLAVE
    0.07
    �
    0.07
    (plane
    0.07
    띵
    0.06
    -ret
    0.06
    Act Density 0.010%

    No Known Activations