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

    Neuronpedia

    INDEX
    Explanations

    likes and dislikes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sağ
    -0.07
     luxe
    -0.07
    female
    -0.07
    uminium
    -0.06
     ensued
    -0.06
     fireplace
    -0.06
    ils
    -0.06
     あ
    -0.06
     heart
    -0.06
     hinted
    -0.06
    POSITIVE LOGITS
    .");
↵
    0.07
    []{↵
    0.06
    ै।↵
    0.06
    ($('.
    0.06
    lobber
    0.06
     Opinion
    0.06
    #:
    0.06
    ))}↵
    0.05
    塞
    0.05
    Conclusion
    0.05
    Act Density 0.077%

    No Known Activations