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

    Neuronpedia

    INDEX
    Explanations

    data comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Unit
    -0.07
     Sai
    -0.07
    ней
    -0.07
     mano
    -0.06
     海
    -0.06
     Лю
    -0.06
     hö
    -0.06
    })();
    -0.06
    κυ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    	tab
    0.07
    publication
    0.07
    èles
    0.06
    -prefix
    0.06
    auty
    0.06
     Ar
    0.06
    τερα
    0.06
    ,:),
    0.06
     created
    0.06
    .pictureBox
    0.06
    Act Density 0.285%

    No Known Activations