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

    Neuronpedia

    INDEX
    Explanations

    alt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     온
    -0.07
     OFF
    -0.07
     Considering
    -0.06
    Reached
    -0.06
    _BUFF
    -0.06
     habits
    -0.06
    finally
    -0.06
     gió
    -0.06
     expect
    -0.06
     colleg
    -0.06
    POSITIVE LOGITS
    辅
    0.07
                     
    0.07
     Dublin
    0.06
     зміст
    0.06
    premium
    0.06
     Rin
    0.06
     відом
    0.06
    ۲۸
    0.06
     Middle
    0.06
     Tradable
    0.06
    Act Density 0.000%

    No Known Activations