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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pistols
    -0.08
     Lok
    -0.07
     hương
    -0.07
    빙
    -0.07
     Trường
    -0.07
     POINTER
    -0.07
    文科
    -0.07
    (Component
    -0.06
    dig
    -0.06
    (Token
    -0.06
    POSITIVE LOGITS
    ged
    0.07
    蔓延
    0.07
     Miche
    0.07
    Ster
    0.07
    س
    0.07
    learn
    0.07
     endforeach
    0.06
    כ
    0.06
    就越
    0.06
     rõ
    0.06
    Act Density 0.006%

    No Known Activations