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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ınıf
    -0.06
     subsection
    -0.06
    	mode
    -0.06
    มหาว
    -0.06
     batteries
    -0.06
    еним
    -0.06
     [↵
    -0.06
    .make
    -0.06
     militants
    -0.06
     Pert
    -0.06
    POSITIVE LOGITS
     moon
    0.11
     Moon
    0.09
     slender
    0.09
     lessen
    0.08
    247
    0.06
     보내
    0.06
    jam
    0.06
     neg
    0.06
     ور
    0.06
     shortage
    0.06
    Act Density 0.004%

    No Known Activations