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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newText
    -0.07
     Кроме
    -0.07
    !");
↵
    -0.07
    Ин
    -0.06
    -sup
    -0.06
    Strange
    -0.06
    لوب
    -0.06
     asi
    -0.06
     बनन
    -0.06
    Nhap
    -0.06
    POSITIVE LOGITS
    .sc
    0.07
    ـ
    0.07
     forks
    0.06
     Hip
    0.06
    (columns
    0.06
     Instructor
    0.06
    .ip
    0.06
    ــ
    0.06
    .poster
    0.06
    large
    0.06
    Act Density 0.005%

    No Known Activations