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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _heap
    -0.07
     trapping
    -0.06
    .buffer
    -0.06
     threatening
    -0.06
     copper
    -0.06
     applications
    -0.06
     Ember
    -0.06
     продуктов
    -0.06
    edores
    -0.06
     Shadows
    -0.06
    POSITIVE LOGITS
    ■■
    0.07
     وع
    0.06
    /GPL
    0.06
     noexcept
    0.06
     conglomer
    0.06
    尊
    0.06
     Ara
    0.06
    =str
    0.06
     '<%=
    0.06
     waited
    0.06
    Act Density 0.129%

    No Known Activations