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

    Neuronpedia

    INDEX
    Explanations

    conversations in professional settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    انا
    -0.06
     Ngân
    -0.06
     dib
    -0.06
    _One
    -0.06
     phố
    -0.06
    _ALPHA
    -0.06
     žád
    -0.05
     حمل
    -0.05
    １
    -0.05
    (drop
    -0.05
    POSITIVE LOGITS
     Provider
    0.07
    /tests
    0.07
    geber
    0.07
     Loves
    0.07
    �
    0.06
    =?
    0.06
    annotations
    0.06
     swearing
    0.06
     />);↵
    0.06
     gente
    0.06
    Act Density 0.172%

    No Known Activations