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

    Neuronpedia

    INDEX
    Explanations

    job responsibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mus
    -0.08
     held
    -0.07
    מרכ
    -0.07
     opposing
    -0.06
    ⡱
    -0.06
     analyzes
    -0.06
    퍿
    -0.06
     Tiles
    -0.06
    岣
    -0.06
    Ms
    -0.06
    POSITIVE LOGITS
    经济技术
    0.08
    Digit
    0.07
    _words
    0.06
    青春
    0.06
    _encrypt
    0.06
    )?;↵↵
    0.06
     familia
    0.06
    สล
    0.06
    صلا
    0.06
    لم
    0.06
    Act Density 0.068%

    No Known Activations