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

    Neuronpedia

    INDEX
    Explanations

    lower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agu
    -0.08
     licence
    -0.08
     Edmond
    -0.07
    所以
    -0.07
     Lic
    -0.07
     licença
    -0.07
     Rd
    -0.07
    ked
    -0.07
     renomm
    -0.07
     Mounted
    -0.07
    POSITIVE LOGITS
    keits
    0.08
     सामाजिक
    0.08
     बन
    0.08
     allgeme
    0.08
    पास
    0.08
     बताए
    0.08
     возраста
    0.08
     harán
    0.08
    गल
    0.08
     allgemeinen
    0.08
    Act Density 0.004%

    No Known Activations