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

    Neuronpedia

    INDEX
    Explanations

    thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     binh
    -0.06
    (batch
    -0.06
     localtime
    -0.06
    yaml
    -0.06
     dB
    -0.06
    兵
    -0.05
     doby
    -0.05
    _b
    -0.05
     given
    -0.05
    سبب
    -0.05
    POSITIVE LOGITS
     Habit
    0.07
    ({↵↵
    0.07
    ากาศ
    0.07
    ฝ
    0.06
     marzo
    0.06
     черв
    0.06
     Bod
    0.06
    розум
    0.06
    OMEM
    0.06
     lup
    0.06
    Act Density 0.019%

    No Known Activations