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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    0.85
    这不是
    0.82
     從
    0.77
    विरो
    0.77
     그려
    0.75
    에
    0.74
    ckte
    0.74
     reconna
    0.74
    看出
    0.73
    ले
    0.72
    POSITIVE LOGITS
     carrying
    0.95
     machining
    0.92
     servlet
    0.90
     soybean
    0.89
     selling
    0.87
     individualized
    0.85
     soya
    0.85
     artisanal
    0.84
     hosting
    0.84
     coffee
    0.84
    Act Density 0.001%

    No Known Activations