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

    Neuronpedia

    INDEX
    Explanations

    Pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    šen
    -0.07
     CRT
    -0.06
     новый
    -0.06
    STRUCTOR
    -0.06
     squat
    -0.06
    passport
    -0.06
    constants
    -0.06
     mour
    -0.06
    Sun
    -0.06
     نوع
    -0.06
    POSITIVE LOGITS
     Danish
    0.07
     Tiếng
    0.07
    _OCCURRED
    0.07
     Humph
    0.06
    wind
    0.06
    �
    0.06
    .Microsoft
    0.06
    _fc
    0.06
     She
    0.06
    �
    0.06
    Act Density 0.049%

    No Known Activations