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

    Neuronpedia

    INDEX
    Explanations

    -type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odní
    -0.07
    Too
    -0.07
    عة
    -0.06
    _FIFO
    -0.06
    ekt
    -0.06
    扶
    -0.06
    raud
    -0.06
    —↵↵
    -0.06
    ng
    -0.06
    afone
    -0.06
    POSITIVE LOGITS
    lobe
    0.07
     Quảng
    0.07
     Theodore
    0.06
     تغ
    0.06
    .Student
    0.06
     ech
    0.06
    .character
    0.06
    	Description
    0.06
    .op
    0.06
    .fd
    0.06
    Act Density 0.002%

    No Known Activations