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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terminator
    -0.07
    	Request
    -0.06
    няется
    -0.06
     dedication
    -0.06
     accept
    -0.06
     ae
    -0.06
    Lim
    -0.06
    	new
    -0.06
     Mvc
    -0.06
    ражд
    -0.06
    POSITIVE LOGITS
     않았
    0.07
    ~↵↵
    0.07
     تهیه
    0.06
     şirket
    0.06
     jou
    0.06
     `;↵
    0.06
    }>
↵
    0.06
     conseils
    0.06
     진짜
    0.06
     인구
    0.06
    Act Density 0.015%

    No Known Activations