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

    Neuronpedia

    INDEX
    Explanations

    trends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    166
    -0.08
    icom
    -0.07
    -0.07
     valves
    -0.07
     supper
    -0.07
     deaf
    -0.07
     electricity
    -0.07
    137
    -0.07
     защиты
    -0.07
     CHAR
    -0.07
    POSITIVE LOGITS
     trends
    0.17
     trend
    0.17
     Trends
    0.14
     Trend
    0.12
    rends
    0.10
     trendy
    0.08
     สาข
    0.07
    rend
    0.07
     Brenda
    0.07
     unprecedented
    0.07
    Act Density 0.008%

    No Known Activations