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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dresses
    -0.07
     VK
    -0.07
    ',
↵
    -0.07
     lunch
    -0.07
    Push
    -0.07
     Dur
    -0.06
    ấn
    -0.06
     Раз
    -0.06
    Lex
    -0.06
    thenReturn
    -0.06
    POSITIVE LOGITS
    tyard
    0.06
     möchte
    0.06
     oblasti
    0.06
    са
    0.06
    ült
    0.06
     IsPlainOldData
    0.06
    記事
    0.06
     chloride
    0.06
    %;">↵
    0.06
     QGraphics
    0.06
    Act Density 0.129%

    No Known Activations