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

    Neuronpedia

    INDEX
    Explanations

    after + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Soon
    0.41
     пой
    0.36
     временем
    0.36
     Once
    0.36
     способом
    0.36
    FlowNode
    0.35
     जिसने
    0.35
    ዲስ
    0.35
    relating
    0.35
    চিত্রে
    0.34
    POSITIVE LOGITS
    尚
    0.37
     बढ़त
    0.35
     tried
    0.34
    astikan
    0.33
    ⁢</
    0.33
     satisfactorily
    0.32
    noons
    0.32
    分隔
    0.32
     shelving
    0.31
    icea
    0.31
    Act Density 0.024%

    No Known Activations