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

    Neuronpedia

    INDEX
    Explanations

    crest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jeep
    -0.07
    ombine
    -0.07
    �
    -0.07
    יחוד
    -0.07
    *\
    -0.07
    的功效
    -0.07
    柩
    -0.07
     апп
    -0.07
     المسلحة
    -0.07
    inherits
    -0.06
    POSITIVE LOGITS
    برا
    0.07
    тен
    0.07
    writer
    0.07
    HOUSE
    0.07
    不到
    0.07
     Brussels
    0.07
     scala
    0.07
    物质
    0.06
    jan
    0.06
    🔛
    0.06
    Act Density 0.001%

    No Known Activations