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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    으나
    -0.08
     Bạn
    -0.07
     на
    -0.07
    اطق
    -0.07
    %%*/
    -0.07
     가
    -0.07
     lname
    -0.07
    }),
    -0.07
    (phase
    -0.07
    
    -0.06
    POSITIVE LOGITS
    raries
    0.07
     insignificant
    0.06
     لب
    0.06
    oreal
    0.06
    Shortcut
    0.06
     строитель
    0.06
     راست
    0.06
    ίας
    0.06
    ropriate
    0.06
     affect
    0.06
    Act Density 0.037%

    No Known Activations