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

    Neuronpedia

    INDEX
    Explanations

    something developed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ជាតិ
    0.45
     academically
    0.43
    美味しい
    0.41
    Benefits
    0.40
    Máy
    0.40
     BENEFITS
    0.40
     benefited
    0.39
    фектив
    0.39
    功效
    0.39
    bsen
    0.39
    POSITIVE LOGITS
    န့်
    0.39
    進
    0.37
    ządu
    0.35
    なの
    0.34
    従
    0.34
    กับการ
    0.33
    我会
    0.33
    の上
    0.33
     guarda
    0.33
    กับ
    0.33
    Act Density 0.000%

    No Known Activations