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

    Neuronpedia

    INDEX
    Explanations

    User input/queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     věn
    -0.07
    la
    -0.07
    baru
    -0.07
     HI
    -0.07
     Çocuk
    -0.07
     вывод
    -0.07
     Proud
    -0.07
    _descr
    -0.06
    .Closed
    -0.06
     Crus
    -0.06
    POSITIVE LOGITS
    _YELLOW
    0.07
    情
    0.06
    _behavior
    0.06
    DECL
    0.06
     چت
    0.05
    327
    0.05
    awning
    0.05
     Uncategorized
    0.05
    -power
    0.05
    _${
    0.05
    Act Density 0.008%

    No Known Activations