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

    Neuronpedia

    INDEX
    Explanations

    harmony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DIR
    -0.06
     dishes
    -0.06
     佛
    -0.06
     pesos
    -0.06
     zařízení
    -0.06
     Txt
    -0.06
    Detect
    -0.06
     blat
    -0.06
     otp
    -0.06
     doit
    -0.06
    POSITIVE LOGITS
    -series
    0.07
    ادت
    0.07
    rior
    0.06
     Series
    0.06
     accompanies
    0.06
    ;}
↵
    0.06
    asting
    0.06
     cruising
    0.06
     series
    0.06
        ↵    ↵    ↵    ↵
    0.06
    Act Density 0.002%

    No Known Activations