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

    Neuronpedia

    INDEX
    Explanations

    serve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contained
    -0.08
    gebaut
    -0.08
    तान
    -0.07
    ဏ
    -0.07
    _run
    -0.07
    _description
    -0.07
     conflicts
    -0.07
    �
    -0.07
    ลน์
    -0.07
    vala
    -0.07
    POSITIVE LOGITS
     piercing
    0.08
     dermatitis
    0.07
     عليك
    0.07
     colleague
    0.07
     rechtstreeks
    0.07
     रिस
    0.07
     Bears
    0.07
     pijn
    0.07
     clás
    0.07
     Philosoph
    0.07
    Act Density 0.002%

    No Known Activations