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

    Neuronpedia

    INDEX
    Explanations

    programming and logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     racing
    -0.07
    _optimizer
    -0.06
    .show
    -0.06
    antic
    -0.06
     André
    -0.06
     PM
    -0.06
     penny
    -0.06
    126
    -0.06
    legt
    -0.06
    виг
    -0.06
    POSITIVE LOGITS
     Cosmos
    0.07
    라이
    0.07
    ุงเทพ
    0.06
    іж
    0.06
     getpid
    0.06
     využití
    0.06
    łem
    0.06
    ЕТ
    0.06
    ~=
    0.06
    џџџџџџџџџџџџџџџџ
    0.06
    Act Density 0.025%

    No Known Activations